@delali/narsil 0.1.15 → 0.2.1-next.25

package/dist/languages/twi.d.ts

@@ -1,5 +1,15 @@
-import { L as LanguageModule } from '../language-ONQ3iVDf.js';
+import { L as LanguageModule } from '../language-DB8KG1z5.js';
 
+/**
+ * Twi analysis: the stop word list and the rules that split Twi
+ * 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 `twi`.
+ *
+ * @public
+ */
 declare const twi: LanguageModule;
 
 export { twi };

package/dist/languages/twi.mjs

@@ -1,3 +1,5 @@
+import { withNormalisedSpellings } from '../chunk-GHJWC2E5.mjs';
+
 // src/languages/twi.ts
 var stopWords = /* @__PURE__ */ new Set([
   "me",
@@ -70,12 +72,21 @@ var stopWords = /* @__PURE__ */ new Set([
   "nye",
   "nnye"
 ]);
+var GREEK_EPSILON = /ε/g;
+var OPEN_O_LOOKALIKES = /[ͻↄכ]/g;
+var TWI_OPEN_E = "\u025B";
+var TWI_OPEN_O = "\u0254";
+function normalize(token) {
+  return token.replace(GREEK_EPSILON, TWI_OPEN_E).replace(OPEN_O_LOOKALIKES, TWI_OPEN_O);
+}
 var twi = {
   name: "twi",
+  revision: "1",
   stemmer: null,
-  stopWords,
+  stopWords: withNormalisedSpellings(stopWords, normalize),
+  normalizer: normalize,
   tokenizer: {
-    splitPattern: /[^a-zA-ZɛɔƐƆ0-9]+/gi,
+    splitPattern: /[^a-zA-ZɛɔƐƆŋŊεͻↄכ0-9\p{M}']+/giu,
     normalizeDiacritics: false,
     minTokenLength: 1
   }

package/dist/languages/ukrainian.d.ts

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

package/dist/languages/ukrainian.mjs

@@ -253,13 +253,21 @@ function stem(word) {
 }
 var stopWords = /* @__PURE__ */ new Set([
   "\u0430",
+  "\u0430\u0431\u0438",
+  "\u0430\u0431\u043E",
+  "\u0430\u0432\u0436\u0435\u0436",
+  "\u0430\u0434\u0436\u0435",
   "\u0430\u043B\u0435",
+  "\u0430\u043D\u0456",
   "\u0431",
+  "\u0431\u0430\u0433\u0430\u0442\u043E",
   "\u0431\u0435\u0437",
   "\u0431\u0438",
   "\u0431\u0456\u043B\u044F",
   "\u0431\u0456\u043B\u044C\u0448",
   "\u0431\u043E",
+  "\u0431\u0443\u0434\u0435",
+  "\u0431\u0443\u0434\u0443\u0442\u044C",
   "\u0431\u0443\u0432",
   "\u0431\u0443\u043B\u0430",
   "\u0431\u0443\u043B\u0438",
@@ -267,117 +275,166 @@ var stopWords = /* @__PURE__ */ new Set([
   "\u0431\u0443\u0442\u0438",
   "\u0432",
   "\u0432\u0430\u043C",
+  "\u0432\u0430\u043C\u0438",
   "\u0432\u0430\u0441",
   "\u0432\u0430\u0448",
   "\u0432\u0430\u0448\u0430",
   "\u0432\u0430\u0448\u0435",
   "\u0432\u0430\u0448\u0456",
+  "\u0432\u0436\u0435",
   "\u0432\u0435\u0441\u044C",
   "\u0432\u0438",
+  "\u0432\u0437\u0434\u043E\u0432\u0436",
+  "\u0432\u043D\u0438\u0437",
+  "\u0432\u043D\u0438\u0437\u0443",
   "\u0432\u0456\u0434",
   "\u0432\u0456\u043D",
   "\u0432\u043E\u043D\u0430",
-  "\u0432\u043E\u043D\u043E",
   "\u0432\u043E\u043D\u0438",
+  "\u0432\u043E\u043D\u043E",
   "\u0432\u0441\u0435",
+  "\u0432\u0441\u0435\u0440\u0435\u0434\u0438\u043D\u0456",
+  "\u0432\u0441\u044E",
   "\u0432\u0441\u044F",
   "\u0432\u0441\u0456",
-  "\u0432\u0441\u044E",
-  "\u0433",
-  "\u0434",
+  "\u0432\u0441\u0456\u0445",
   "\u0434\u0430",
-  "\u0434\u0430\u043B\u0438",
-  "\u0434\u0432\u0430",
+  "\u0434\u0430\u0432\u0430\u0439",
+  "\u0434\u0430\u0432\u0430\u0442\u0438",
   "\u0434\u0435",
+  "\u0434\u0435\u043A\u0456\u043B\u044C\u043A\u0430",
   "\u0434\u0435\u0449\u043E",
+  "\u0434\u0435\u044F\u043A\u0456",
+  "\u0434\u043B\u044F",
   "\u0434\u043E",
-  "\u0434\u043E\u0431\u0440\u0435",
-  "\u0434\u0440\u0443\u0433\u0438\u0439",
-  "\u0435",
   "\u0454",
   "\u0436",
+  "\u0436\u0435",
   "\u0437",
   "\u0437\u0430",
+  "\u0437\u0430\u0432\u0436\u0434\u0438",
+  "\u0437\u0430\u043C\u0456\u0441\u0442\u044C",
   "\u0437\u0430\u0440\u0430\u0437",
+  "\u0437\u0430\u0442\u0435",
+  "\u0437\u0432\u0456\u0434\u043A\u0438",
+  "\u0437\u0432\u0456\u0434\u0441\u0438",
+  "\u0437\u0432\u0456\u0434\u0442\u0438",
   "\u0437\u0456",
   "\u0456",
   "\u0456\u0437",
-  "\u0456\u0439",
+  "\u0456\u043D\u043E\u0434\u0456",
   "\u0456\u043D\u043A\u043E\u043B\u0438",
+  "\u0456\u043D\u0448\u0430",
+  "\u0456\u043D\u0448\u0435",
   "\u0456\u043D\u0448\u0438\u0439",
+  "\u0456\u043D\u0448\u0456",
+  "\u0456\u043D\u0448\u0438\u0445",
   "\u0457\u0439",
   "\u0457\u043C",
   "\u0457\u0445",
+  "\u0457\u0445\u043D\u0454",
+  "\u0457\u0445\u043D\u0456",
+  "\u0457\u0445\u043D\u0456\u0439",
+  "\u0457\u0445\u043D\u044F",
   "\u0457\u0457",
   "\u0439",
   "\u0439\u043E\u0433\u043E",
   "\u0439\u043E\u043C\u0443",
-  "\u043A",
+  "\u043A\u043E\u0433\u043E",
   "\u043A\u043E\u0436\u0435\u043D",
   "\u043A\u043E\u0436\u043D\u0430",
+  "\u043A\u043E\u0436\u043D\u0435",
   "\u043A\u043E\u043B\u0438",
-  "\u043A\u043E\u0442\u0440\u0438\u0439",
-  "\u043A\u043E\u0442\u0440\u0430",
+  "\u043A\u043E\u043B\u043E",
   "\u043A\u043E\u043C\u0443",
+  "\u043A\u043E\u0442\u0440\u0430",
+  "\u043A\u043E\u0442\u0440\u0435",
+  "\u043A\u043E\u0442\u0440\u0438\u0439",
+  "\u043A\u043E\u0442\u0440\u0456",
   "\u043A\u0440\u0456\u043C",
-  "\u043B",
-  "\u043C",
+  "\u043A\u0443\u0434\u0438",
+  "\u043A\u0456\u043B\u044C\u043A\u0430",
+  "\u043B\u0435\u0434\u0432\u0435",
+  "\u043B\u0438\u0448\u0435",
+  "\u043C\u0430\u0439\u0436\u0435",
+  "\u043C\u0430\u043B\u043E",
+  "\u043C\u0435\u043D\u0435",
+  "\u043C\u0435\u043D\u0456",
   "\u043C\u0438",
-  "\u043C\u0456\u0436",
-  "\u043C\u0456\u0439",
   "\u043C\u043D\u043E\u044E",
+  "\u043C\u043E\u0432",
   "\u043C\u043E\u0433\u043E",
-  "\u043C\u043E\u0436\u0435",
-  "\u043C\u043E\u0436\u043D\u0430",
-  "\u043C\u043E\u044F",
-  "\u043C\u043E\u0454",
   "\u043C\u043E\u0454\u043C\u0443",
   "\u043C\u043E\u0457\u0439",
   "\u043C\u043E\u0457\u0445",
   "\u043C\u043E\u044E",
-  "\u043D",
+  "\u043C\u043E\u0436\u0435",
+  "\u043C\u043E\u0436\u043D\u0430",
+  "\u043C\u043E\u044F",
+  "\u043C\u043E\u0454",
+  "\u043C\u043E\u0457",
+  "\u043C\u0456\u0439",
+  "\u043C\u0456\u0436",
   "\u043D\u0430",
+  "\u043D\u0430\u0432\u043A\u043E\u043B\u043E",
   "\u043D\u0430\u0432\u0456\u0442\u044C",
   "\u043D\u0430\u0434",
   "\u043D\u0430\u043C",
+  "\u043D\u0430\u043C\u0438",
   "\u043D\u0430\u0441",
+  "\u043D\u0430\u0447\u0435",
   "\u043D\u0430\u0448",
   "\u043D\u0430\u0448\u0430",
   "\u043D\u0430\u0448\u0435",
   "\u043D\u0430\u0448\u0438\u0445",
+  "\u043D\u0430\u0448\u0456",
   "\u043D\u0435",
+  "\u043D\u0435\u043C\u043E\u0432",
+  "\u043D\u0435\u044E",
+  "\u043D\u0435\u0457",
+  "\u043D\u0438\u043C",
+  "\u043D\u0438\u043C\u0438",
+  "\u043D\u0438\u0445",
+  "\u043D\u044C\u043E\u0433\u043E",
+  "\u043D\u044C\u043E\u043C\u0443",
   "\u043D\u0456",
+  "\u043D\u0456\u0431\u0438",
   "\u043D\u0456\u0436",
+  "\u043D\u0456\u043A\u043E\u0433\u043E",
   "\u043D\u0456\u043A\u043E\u043B\u0438",
+  "\u043D\u0456\u0445\u0442\u043E",
+  "\u043D\u0456\u0449\u043E",
   "\u043D\u0456\u0447\u043E\u0433\u043E",
-  "\u043E",
-  "\u043E\u0431\u0438\u0434\u0432\u0430",
-  "\u043E\u0434\u0438\u043D",
   "\u043E\u0434\u043D\u0430\u043A",
-  "\u043E\u0434\u043D\u0430",
-  "\u043E\u0434\u043D\u0435",
-  "\u043E\u0434\u043D\u0456",
-  "\u043F",
-  "\u043F\u0456\u0434",
-  "\u043F\u0456\u0441\u043B\u044F",
+  "\u043E\u043A\u0440\u0456\u043C",
+  "\u043E\u0442",
+  "\u043E\u0442\u0436\u0435",
+  "\u043E\u0442\u043E\u0436",
+  "\u043F\u0435\u0440\u0435\u0434",
   "\u043F\u043E",
+  "\u043F\u043E\u0437\u0430",
   "\u043F\u0440\u0438",
   "\u043F\u0440\u043E",
-  "\u0440",
-  "\u0440\u0430\u0437",
-  "\u0441",
+  "\u043F\u0440\u043E\u0442\u0435",
+  "\u043F\u0440\u043E\u0442\u0438",
+  "\u043F\u0456\u0434",
+  "\u043F\u0456\u0441\u043B\u044F",
   "\u0441\u0430\u043C",
   "\u0441\u0430\u043C\u0430",
   "\u0441\u0430\u043C\u0435",
   "\u0441\u0430\u043C\u0456",
-  "\u0441\u0432\u0456\u0439",
   "\u0441\u0432\u043E\u0433\u043E",
   "\u0441\u0432\u043E\u044E",
+  "\u0441\u0432\u043E\u044F",
+  "\u0441\u0432\u043E\u0454",
   "\u0441\u0432\u043E\u0457",
+  "\u0441\u0432\u0456\u0439",
   "\u0441\u0435\u0431\u0435",
   "\u0441\u0435\u0440\u0435\u0434",
-  "\u0441\u044F",
-  "\u0442",
+  "\u0441\u043A\u0456\u043B\u044C\u043A\u0438",
+  "\u0441\u043E\u0431\u0456",
+  "\u0441\u043E\u0431\u043E\u044E",
+  "\u0441\u044E\u0434\u0438",
   "\u0442\u0430",
   "\u0442\u0430\u043A",
   "\u0442\u0430\u043A\u043E\u0436",
@@ -392,53 +449,74 @@ var stopWords = /* @__PURE__ */ new Set([
   "\u0442\u0438\u043C",
   "\u0442\u0438\u0445",
   "\u0442\u043E",
+  "\u0442\u043E\u0431\u0442\u043E",
   "\u0442\u043E\u0431\u0456",
+  "\u0442\u043E\u0431\u043E\u044E",
   "\u0442\u043E\u0433\u043E",
   "\u0442\u043E\u0434\u0456",
+  "\u0442\u043E\u0439",
   "\u0442\u043E\u043C\u0443",
+  "\u0442\u043E\u0436",
+  "\u0442\u043E\u0449\u043E",
+  "\u0442\u0443",
+  "\u0442\u0443\u0434\u0438",
   "\u0442\u0443\u0442",
+  "\u0442\u0456",
+  "\u0442\u0456\u0439",
+  "\u0442\u0456\u043B\u044C\u043A\u0438",
   "\u0443",
   "\u0443\u0432\u0435\u0441\u044C",
+  "\u0443\u0436\u0435",
   "\u0443\u0441\u0435",
   "\u0443\u0441\u0456",
   "\u0443\u0441\u044E",
   "\u0443\u0441\u044F",
-  "\u0444",
-  "\u0445",
   "\u0445\u0430\u0439",
   "\u0445\u043E\u0447",
   "\u0445\u043E\u0447\u0430",
   "\u0445\u0442\u043E",
-  "\u0446",
+  "\u0445\u0442\u043E\u0441\u044C",
   "\u0446\u0435",
   "\u0446\u0435\u0439",
-  "\u0446\u044F",
-  "\u0446\u044C\u043E\u0433\u043E",
   "\u0446\u0438\u043C",
+  "\u0446\u0438\u0445",
+  "\u0446\u044C\u043E\u0433\u043E",
+  "\u0446\u044C\u043E\u043C\u0443",
+  "\u0446\u044E",
+  "\u0446\u044F",
   "\u0446\u0456",
   "\u0446\u0456\u0439",
-  "\u0446\u044E",
-  "\u0447",
+  "\u0447\u0430\u0441\u0442\u043E",
+  "\u0447\u0435\u0440\u0435\u0437",
   "\u0447\u0438",
   "\u0447\u0438\u0439",
+  "\u0447\u0438\u044F",
+  "\u0447\u0438\u0454",
+  "\u0447\u0438\u0457",
   "\u0447\u043E\u0433\u043E",
   "\u0447\u043E\u043C\u0443",
-  "\u0448",
+  "\u0449\u0435",
   "\u0449\u043E",
   "\u0449\u043E\u0431",
+  "\u0449\u043E\u0431\u0438",
+  "\u0449\u043E\u0434\u043E",
   "\u0449\u043E\u0441\u044C",
   "\u044F",
   "\u044F\u043A",
   "\u044F\u043A\u0430",
+  "\u044F\u043A\u0431\u0438",
   "\u044F\u043A\u0435",
+  "\u044F\u043A\u0438\u0439",
+  "\u044F\u043A\u0449\u043E",
   "\u044F\u043A\u0456",
-  "\u044F\u043A\u0449\u043E"
+  "\u044F\u043A\u043E\u0457"
 ]);
 var ukrainian = {
   name: "ukrainian",
+  revision: "1",
   stemmer: stem,
   stopWords,
-  tokenizer: { splitPattern: /[^a-z0-9а-яіїєґ]+/gi }
+  tokenizer: { splitPattern: /[^a-z0-9а-яіїєґ']+/gi }
 };
 
 export { ukrainian };

package/dist/languages/urdu.d.ts

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