@delali/narsil 0.1.15 → 0.2.1-next.25

package/dist/languages/lao.mjs

@@ -0,0 +1,63 @@
+// src/languages/lao.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "\u0E81\u0ECD",
+  "\u0E81\u0EB1\u0E99",
+  "\u0E81\u0EB1\u0E9A",
+  "\u0E82\u0ECD",
+  "\u0E82\u0EB6\u0EC9\u0E99",
+  "\u0E84\u0EB1\u0EC9\u0E87",
+  "\u0E84\u0EB7",
+  "\u0E84\u0EBB\u0E87",
+  "\u0E88\u0EB0",
+  "\u0E88\u0EB1\u0E94",
+  "\u0E88\u0EB6\u0EC8\u0E87",
+  "\u0EAA\u0EB4\u0EC8\u0E87",
+  "\u0EAA\u0EB8\u0E94",
+  "\u0EAA\u0EBB\u0EC8\u0E87",
+  "\u0E8D\u0EB1\u0E87",
+  "\u0E94\u0EB1\u0E87",
+  "\u0EC4\u0E94\u0EC9",
+  "\u0E95\u0ECD\u0EC8",
+  "\u0E95\u0EB1\u0EC9\u0E87",
+  "\u0EC1\u0E95\u0EC8",
+  "\u0E96\u0EC9\u0EB2",
+  "\u0E96\u0EB7\u0E81",
+  "\u0E97\u0EB1\u0E87",
+  "\u0E97\u0EB5\u0EC8",
+  "\u0E97\u0EB8\u0E81",
+  "\u0E99\u0EB1\u0E81",
+  "\u0E99\u0EB1\u0EC9\u0E99",
+  "\u0E99\u0ECD\u0EB2",
+  "\u0E99\u0EB5\u0EC9",
+  "\u0EC3\u0E99",
+  "\u0E9A\u0ECD\u0EC8",
+  "\u0EC4\u0E9B",
+  "\u0E9C\u0EBB\u0E99",
+  "\u0E9E\u0EBB\u0E9A",
+  "\u0EA1\u0EB2",
+  "\u0EA1\u0EB5",
+  "\u0EA1\u0EB7\u0EC9",
+  "\u0EA2\u0EB9\u0EC8",
+  "\u0EA5\u0EBB\u0E87",
+  "\u0EA7\u0EC8\u0EB2",
+  "\u0EC4\u0EA7\u0EC9",
+  "\u0EAB\u0EA5\u0EB7",
+  "\u0EAB\u0EBC\u0EB7",
+  "\u0EC3\u0EAB\u0EC9",
+  "\u0EAD\u0EB5\u0E81",
+  "\u0EAE\u0EB1\u0E9A"
+]);
+var lao = {
+  name: "lao",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: {
+    splitPattern: /[^ກ-ໟa-z0-9]+/giu,
+    normalizeDiacritics: false,
+    minTokenLength: 1,
+    ngramSize: 2
+  }
+};
+
+export { lao };

package/dist/languages/latin.d.ts

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

package/dist/languages/latin.mjs

@@ -0,0 +1,69 @@
+import { removeMarks } from '../chunk-KH3YGMVT.mjs';
+import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
+
+// src/languages/latin.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "a",
+  "ab",
+  "ac",
+  "ad",
+  "at",
+  "atque",
+  "aut",
+  "autem",
+  "cum",
+  "de",
+  "dum",
+  "e",
+  "erant",
+  "erat",
+  "est",
+  "et",
+  "etiam",
+  "ex",
+  "haec",
+  "hic",
+  "hoc",
+  "in",
+  "ita",
+  "me",
+  "nec",
+  "neque",
+  "non",
+  "per",
+  "qua",
+  "quae",
+  "quam",
+  "qui",
+  "quibus",
+  "quidem",
+  "quo",
+  "quod",
+  "re",
+  "rebus",
+  "rem",
+  "res",
+  "sed",
+  "si",
+  "sic",
+  "sunt",
+  "tamen",
+  "tandem",
+  "te",
+  "ut",
+  "vel"
+]);
+var MACRON = /\u0304/g;
+function normalize(token) {
+  return removeMarks(token, MACRON);
+}
+var latin = {
+  name: "latin",
+  revision: "1",
+  stemmer: null,
+  stopWords: withNormalisedSpellings(stopWords, normalize),
+  normalizer: normalize,
+  tokenizer: { splitPattern: /[^a-z0-9āēīōū]+/gi }
+};
+
+export { latin };

package/dist/languages/latvian.d.ts

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

package/dist/languages/latvian.mjs

@@ -0,0 +1,173 @@
+// src/languages/latvian.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "aiz",
+  "ap",
+  "apak\u0161",
+  "apak\u0161pus",
+  "ar",
+  "ar\u012B",
+  "\u0101rpus",
+  "aug\u0161pus",
+  "bet",
+  "bez",
+  "bija",
+  "bij\u0101m",
+  "bij\u0101t",
+  "biji",
+  "biju",
+  "b\u016Bs",
+  "b\u016Bsi",
+  "b\u016Bsiet",
+  "b\u016Bsim",
+  "b\u016B\u0161u",
+  "b\u016Bt",
+  "caur",
+  "d\u0113\u013C",
+  "diem\u017E\u0113l",
+  "diezin",
+  "dro\u0161i",
+  "esam",
+  "esat",
+  "esi",
+  "esmu",
+  "gan",
+  "gar",
+  "iekam",
+  "iek\u0101m",
+  "iekams",
+  "iek\u0101ms",
+  "iek\u0161",
+  "iek\u0161pus",
+  "ik",
+  "ir",
+  "it",
+  "itin",
+  "iz",
+  "ja",
+  "j\u0101",
+  "jau",
+  "jeb",
+  "jeb\u0161u",
+  "jel",
+  "jo",
+  "ka",
+  "k\u0101",
+  "kam\u0113r",
+  "kaut",
+  "k\u013C\u016Bs",
+  "k\u013C\u016Bsi",
+  "k\u013C\u016Bsiet",
+  "k\u013C\u016Bsim",
+  "k\u013C\u016Bst",
+  "k\u013C\u016Bstam",
+  "k\u013C\u016Bstat",
+  "k\u013C\u016Bsti",
+  "k\u013C\u016Bstu",
+  "k\u013C\u016B\u0161u",
+  "k\u013C\u016Bt",
+  "k\u013Cuva",
+  "k\u013Cuv\u0101m",
+  "k\u013Cuv\u0101t",
+  "k\u013Cuvi",
+  "k\u013Cuvu",
+  "kol\u012Bdz",
+  "kop\u0161",
+  "labad",
+  "lai",
+  "lejpus",
+  "l\u012Bdz",
+  "l\u012Bdzko",
+  "ne",
+  "n\u0113",
+  "neb\u016Bt",
+  "nedz",
+  "nek\u0101",
+  "nevis",
+  "nezin",
+  "no",
+  "nu",
+  "otrpus",
+  "pa",
+  "par",
+  "p\u0101r",
+  "pat",
+  "p\u0113c",
+  "pie",
+  "pirms",
+  "pret",
+  "priek\u0161",
+  "\u0161aipus",
+  "starp",
+  "t\u0101",
+  "ta\u010Du",
+  "tad",
+  "t\u0101d\u0113\u013C",
+  "tak",
+  "t\u0101lab",
+  "tap\u0101t",
+  "t\u0101p\u0113c",
+  "tapi",
+  "taps",
+  "tapsi",
+  "tapsiet",
+  "tapsim",
+  "tap\u0161u",
+  "tapt",
+  "te",
+  "tiec",
+  "tiek",
+  "tiekam",
+  "tiekat",
+  "tieku",
+  "tik",
+  "tika",
+  "tikai",
+  "tik\u0101m",
+  "tik\u0101t",
+  "tiki",
+  "tikko",
+  "tiklab",
+  "tikl\u012Bdz",
+  "tiks",
+  "tiksiet",
+  "tiksim",
+  "tik\u0161u",
+  "tikt",
+  "tiku",
+  "tikvien",
+  "tom\u0113r",
+  "topat",
+  "turpret\u012B",
+  "turpretim",
+  "un",
+  "uz",
+  "vai",
+  "var",
+  "varat",
+  "var\u0113ja",
+  "var\u0113j\u0101m",
+  "var\u0113j\u0101t",
+  "var\u0113ji",
+  "var\u0113ju",
+  "var\u0113s",
+  "var\u0113si",
+  "var\u0113siet",
+  "var\u0113sim",
+  "var\u0113\u0161u",
+  "var\u0113t",
+  "vien",
+  "vi\u0146pus",
+  "virs",
+  "virspus",
+  "vis",
+  "zem"
+]);
+var latvian = {
+  name: "latvian",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^a-z0-9āčēģīķļņšūž]+/gi }
+};
+
+export { latvian };

package/dist/languages/lingala.d.ts

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

package/dist/languages/lingala.mjs

@@ -0,0 +1,61 @@
+// src/languages/lingala.ts
+var stopWords = /* @__PURE__ */ new Set([
+  "awa",
+  "azalaki",
+  "azali",
+  "bango",
+  "basusu",
+  "bazali",
+  "bino",
+  "biso",
+  "bongo",
+  "boye",
+  "epai",
+  "ezalaki",
+  "ezali",
+  "kaka",
+  "kasi",
+  "kati",
+  "kuna",
+  "liboso",
+  "likolo",
+  "lisusu",
+  "lokola",
+  "mingi",
+  "misusu",
+  "moko",
+  "mosusu",
+  "mpe",
+  "mpo",
+  "na",
+  "naino",
+  "nazali",
+  "ngai",
+  "nse",
+  "nsima",
+  "nyonso",
+  "oyo",
+  "ozali",
+  "pe",
+  "sikawa",
+  "sikoyo",
+  "sima",
+  "soki",
+  "te",
+  "tii",
+  "to",
+  "tozali",
+  "wana",
+  "ya",
+  "ye",
+  "yo"
+]);
+var lingala = {
+  name: "lingala",
+  revision: "1",
+  stemmer: null,
+  stopWords,
+  tokenizer: { splitPattern: /[^\p{Script=Latin}\p{M}0-9]+/giu }
+};
+
+export { lingala };

package/dist/languages/lithuanian.d.ts

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