wikitongues-db 0.2.2 → 0.2.3

package/dist/{dataset-DNYcpFFZ.d.mts → dataset-Bh9bZBtJ.d.mts}

@@ -125,6 +125,7 @@ interface ResolvedBcp47 {
     regionSubtag?: string;
     variantSubtags: string[];
     description?: string;
+    macrolanguage?: string;
 }
 interface ResolvedStandards {
     iso639_3: ResolvedIso639_3;

package/dist/{dataset-DNYcpFFZ.d.ts → dataset-Bh9bZBtJ.d.ts}

@@ -125,6 +125,7 @@ interface ResolvedBcp47 {
     regionSubtag?: string;
     variantSubtags: string[];
     description?: string;
+    macrolanguage?: string;
 }
 interface ResolvedStandards {
     iso639_3: ResolvedIso639_3;

package/dist/dataset.d.mts

@@ -1 +1 @@
-export { l as dataset, l as default } from './dataset-DNYcpFFZ.mjs';
+export { l as dataset, l as default } from './dataset-Bh9bZBtJ.mjs';

package/dist/dataset.d.ts

@@ -1 +1 @@
-export { l as dataset, l as default } from './dataset-DNYcpFFZ.js';
+export { l as dataset, l as default } from './dataset-Bh9bZBtJ.js';

package/dist/index.d.mts

@@ -1,5 +1,5 @@
-import { R as ReferenceTables, a as ResolvedIso639_3, b as ResolvedGlottolog, c as ResolvedBcp47, S as StandardsData, d as ResolvedStandards, L as LanguageData, e as SpeakerData, P as ProvenanceData, T as TranscriptionData, f as RawMetadataData, V as VideoData, F as FilterOptions, g as LanguageSummary, C as CountrySummary, h as SpeakerSummary, D as DatasetStats } from './dataset-DNYcpFFZ.mjs';
-export { G as GlottologEntry, I as IanaLanguageEntry, i as IanaSubtagEntry, j as IanaVariantEntry, k as Iso639_3Entry, l as dataset } from './dataset-DNYcpFFZ.mjs';
+import { R as ReferenceTables, a as ResolvedIso639_3, b as ResolvedGlottolog, c as ResolvedBcp47, S as StandardsData, d as ResolvedStandards, L as LanguageData, e as SpeakerData, P as ProvenanceData, T as TranscriptionData, f as RawMetadataData, V as VideoData, F as FilterOptions, g as LanguageSummary, C as CountrySummary, h as SpeakerSummary, D as DatasetStats } from './dataset-Bh9bZBtJ.mjs';
+export { G as GlottologEntry, I as IanaLanguageEntry, i as IanaSubtagEntry, j as IanaVariantEntry, k as Iso639_3Entry, l as dataset } from './dataset-Bh9bZBtJ.mjs';
 
 /**
  * Deterministic hydration of the persisted ontological anchor keys
@@ -193,6 +193,10 @@ declare class VideoCollection implements Iterable<Video> {
     toArray(): Video[];
     slice(start?: number, end?: number): VideoCollection;
     includes(item: Video | string): boolean;
+    /**
+     * Check if any video in the collection matches the given language query.
+     */
+    hasLanguage(query: string): boolean;
     get isEmpty(): boolean;
     get ids(): string[];
     get urls(): string[];
@@ -416,6 +420,11 @@ declare class WikitonguesDB {
      * classifications, Glottolog / ISO names and speaker claims.
      */
     findByLanguage(languageQuery: string, includeAdditional?: boolean): VideoCollection;
+    /**
+     * Check if the database contains any video matching the language query
+     * (by ISO 639-3, ISO 639-1, BCP 47, macrolanguage, or name).
+     */
+    hasLanguage(query: string): boolean;
     /**
      * Shortcut method to filter videos by common criteria.
      */

package/dist/index.d.ts

@@ -1,5 +1,5 @@
-import { R as ReferenceTables, a as ResolvedIso639_3, b as ResolvedGlottolog, c as ResolvedBcp47, S as StandardsData, d as ResolvedStandards, L as LanguageData, e as SpeakerData, P as ProvenanceData, T as TranscriptionData, f as RawMetadataData, V as VideoData, F as FilterOptions, g as LanguageSummary, C as CountrySummary, h as SpeakerSummary, D as DatasetStats } from './dataset-DNYcpFFZ.js';
-export { G as GlottologEntry, I as IanaLanguageEntry, i as IanaSubtagEntry, j as IanaVariantEntry, k as Iso639_3Entry, l as dataset } from './dataset-DNYcpFFZ.js';
+import { R as ReferenceTables, a as ResolvedIso639_3, b as ResolvedGlottolog, c as ResolvedBcp47, S as StandardsData, d as ResolvedStandards, L as LanguageData, e as SpeakerData, P as ProvenanceData, T as TranscriptionData, f as RawMetadataData, V as VideoData, F as FilterOptions, g as LanguageSummary, C as CountrySummary, h as SpeakerSummary, D as DatasetStats } from './dataset-Bh9bZBtJ.js';
+export { G as GlottologEntry, I as IanaLanguageEntry, i as IanaSubtagEntry, j as IanaVariantEntry, k as Iso639_3Entry, l as dataset } from './dataset-Bh9bZBtJ.js';
 
 /**
  * Deterministic hydration of the persisted ontological anchor keys
@@ -193,6 +193,10 @@ declare class VideoCollection implements Iterable<Video> {
     toArray(): Video[];
     slice(start?: number, end?: number): VideoCollection;
     includes(item: Video | string): boolean;
+    /**
+     * Check if any video in the collection matches the given language query.
+     */
+    hasLanguage(query: string): boolean;
     get isEmpty(): boolean;
     get ids(): string[];
     get urls(): string[];
@@ -416,6 +420,11 @@ declare class WikitonguesDB {
      * classifications, Glottolog / ISO names and speaker claims.
      */
     findByLanguage(languageQuery: string, includeAdditional?: boolean): VideoCollection;
+    /**
+     * Check if the database contains any video matching the language query
+     * (by ISO 639-3, ISO 639-1, BCP 47, macrolanguage, or name).
+     */
+    hasLanguage(query: string): boolean;
     /**
      * Shortcut method to filter videos by common criteria.
      */

package/dist/index.js

@@ -219,7 +219,13 @@ var MULTILINGUAL_ALIASES = {
   sw: "swh",
   so: "som",
   zu: "zul",
-  xh: "xho"
+  xh: "xho",
+  et: "est",
+  az: "aze",
+  lv: "lav",
+  ne: "nep",
+  ff: "ful",
+  mg: "mlg"
 };
 var MACROLANGUAGE_EXPANSIONS = {
   fas: ["fas", "pes", "prs"],
@@ -268,7 +274,10 @@ var MACROLANGUAGE_EXPANSIONS = {
   est: ["est", "ekk", "vro"],
   aka: ["aka", "twi", "fat"],
   nep: ["nep", "npi"],
-  ful: ["ful", "fuf", "fuh", "fub", "fuq"]
+  ful: ["ful", "fuf", "fuh", "fub", "fuq"],
+  lav: ["lav", "lvs", "ltg"],
+  mon: ["mon", "khk", "mvf"],
+  mlg: ["mlg", "plt", "skg", "tkg"]
 };
 var LanguageResolver = class {
   isoToName = /* @__PURE__ */ new Map();
@@ -310,6 +319,14 @@ var LanguageResolver = class {
         this.aliases.set(prefix, iso);
       }
     }
+    const part1 = lang.standards.iso639_3.part1?.toLowerCase();
+    if (part1 && !this.aliases.has(part1)) {
+      this.aliases.set(part1, iso);
+    }
+    const macro = lang.standards.bcp47.macrolanguage?.toLowerCase();
+    if (macro && !this.aliases.has(macro)) {
+      this.aliases.set(macro, iso);
+    }
     const gc = lang.glottocode;
     this.glottoToIso.set(gc, iso);
     this.isoToGlotto.set(iso, gc);
@@ -375,7 +392,7 @@ var LanguageResolver = class {
         }
       }
     }
-    if (matchedIsos.size === 0) {
+    if (matchedIsos.size === 0 && norm.length >= 4) {
       for (const [autoKey, isoSet] of this.autonymToIso.entries()) {
         if (autoKey.includes(norm)) {
           for (const iso of isoSet) {
@@ -9902,6 +9919,7 @@ var ReferenceHydrator = class {
     }
     const resolved = { tag: raw, primarySubtag: primary, variantSubtags: [] };
     if (lang.description) resolved.description = lang.description;
+    if (lang.macrolanguage) resolved.macrolanguage = lang.macrolanguage;
     let state = 0;
     for (const sub of parts.slice(1)) {
       const lower = sub.toLowerCase();
@@ -10183,6 +10201,8 @@ var Video = class _Video {
     const set = /* @__PURE__ */ new Set();
     for (const lang of this.allLanguages) {
       if (lang.iso639_3) set.add(lang.iso639_3);
+      if (lang.standards.iso639_3.part1) set.add(lang.standards.iso639_3.part1);
+      if (lang.standards.bcp47.macrolanguage) set.add(lang.standards.bcp47.macrolanguage);
     }
     return set;
   }
@@ -10193,6 +10213,9 @@ var Video = class _Video {
     const set = /* @__PURE__ */ new Set();
     for (const lang of this.allLanguages) {
       if (lang.bcp47) set.add(lang.bcp47);
+      if (lang.iso639_3) set.add(lang.iso639_3);
+      if (lang.standards.iso639_3.part1) set.add(lang.standards.iso639_3.part1);
+      if (lang.standards.bcp47.macrolanguage) set.add(lang.standards.bcp47.macrolanguage);
     }
     return set;
   }
@@ -10230,6 +10253,8 @@ var Video = class _Video {
     const qNorm = normalizeText(q);
     for (const lang of this.allLanguages) {
       if (lang.iso639_3 === qLower) return true;
+      if (lang.standards.iso639_3.part1?.toLowerCase() === qLower) return true;
+      if (lang.standards.bcp47.macrolanguage?.toLowerCase() === qLower) return true;
       const bcp = lang.bcp47.toLowerCase();
       if (bcp === qLower || bcp.startsWith(`${qLower}-`)) return true;
       if (lang.glottocode === qLower) return true;
@@ -10238,7 +10263,8 @@ var Video = class _Video {
         const labelNorm = normalizeText(label);
         if (labelNorm === qNorm || ` ${labelNorm} `.includes(` ${qNorm} `)) return true;
       }
-      if (lang.autonym.toLowerCase().includes(qLower)) return true;
+      const autoLower = lang.autonym.toLowerCase();
+      if (autoLower === qLower || qLower.length >= 4 && autoLower.includes(qLower)) return true;
     }
     return false;
   }
@@ -10346,6 +10372,12 @@ var VideoCollection = class _VideoCollection {
     }
     return this._videos.some((v) => v.id === item.id);
   }
+  /**
+   * Check if any video in the collection matches the given language query.
+   */
+  hasLanguage(query) {
+    return this._videos.some((v) => v.hasLanguage(query));
+  }
   // -------------------------------------------------------------------------
   // Aggregation & Summary Properties
   // -------------------------------------------------------------------------
@@ -10651,7 +10683,7 @@ var DatasetIndex = class {
     const list = map.get(key);
     if (!list) {
       map.set(key, [video]);
-    } else {
+    } else if (!list.some((v) => v.id === video.id)) {
       list.push(video);
     }
   }
@@ -10664,12 +10696,30 @@ var DatasetIndex = class {
       if (plIso) {
         this.appendToMap(this.byIsoPrimary, plIso, video);
         this.appendToMap(this.byIso, plIso, video);
+        const part1 = video.primaryLanguage.standards.iso639_3.part1?.toLowerCase();
+        if (part1 && part1 !== plIso) {
+          this.appendToMap(this.byIsoPrimary, part1, video);
+          this.appendToMap(this.byIso, part1, video);
+        }
+        const macro = video.primaryLanguage.standards.bcp47.macrolanguage?.toLowerCase();
+        if (macro && macro !== plIso && macro !== part1) {
+          this.appendToMap(this.byIsoPrimary, macro, video);
+          this.appendToMap(this.byIso, macro, video);
+        }
       }
       for (const addLang of video.additionalLanguages) {
         const aIso = addLang.iso639_3;
-        if (aIso && aIso !== plIso) {
+        if (aIso) {
           this.appendToMap(this.byIso, aIso, video);
         }
+        const part1 = addLang.standards.iso639_3.part1?.toLowerCase();
+        if (part1 && part1 !== aIso) {
+          this.appendToMap(this.byIso, part1, video);
+        }
+        const macro = addLang.standards.bcp47.macrolanguage?.toLowerCase();
+        if (macro && macro !== aIso && macro !== part1) {
+          this.appendToMap(this.byIso, macro, video);
+        }
       }
       for (const lang of video.allLanguages) {
         const bcp = lang.bcp47.toLowerCase().trim();
@@ -10680,6 +10730,18 @@ var DatasetIndex = class {
             this.appendToMap(this.byBcp47, prefix, video);
           }
         }
+        const iso = lang.iso639_3?.toLowerCase().trim();
+        if (iso && iso !== bcp) {
+          this.appendToMap(this.byBcp47, iso, video);
+        }
+        const part1 = lang.standards.iso639_3.part1?.toLowerCase().trim();
+        if (part1 && part1 !== bcp && part1 !== iso) {
+          this.appendToMap(this.byBcp47, part1, video);
+        }
+        const macro = lang.standards.bcp47.macrolanguage?.toLowerCase().trim();
+        if (macro && macro !== bcp && macro !== iso && macro !== part1) {
+          this.appendToMap(this.byBcp47, macro, video);
+        }
       }
       for (const lang of video.allLanguages) {
         this.appendToMap(this.byGlottocode, lang.glottocode, video);
@@ -10922,6 +10984,14 @@ var QueryBuilder = class _QueryBuilder {
       if (matchedIsos.has(lIso) || lIso === rawLower) {
         return true;
       }
+      const part1 = lang.standards.iso639_3.part1?.toLowerCase();
+      if (part1 && (matchedIsos.has(part1) || part1 === rawLower)) {
+        return true;
+      }
+      const macro = lang.standards.bcp47.macrolanguage?.toLowerCase();
+      if (macro && (matchedIsos.has(macro) || macro === rawLower)) {
+        return true;
+      }
       const lBcp = lang.bcp47.toLowerCase();
       if (lBcp === rawLower || lBcp.startsWith(`${rawLower}-`)) {
         return true;
@@ -10934,7 +11004,9 @@ var QueryBuilder = class _QueryBuilder {
           const lNorm = normalizeText(label);
           if (lNorm === norm || pattern && pattern.test(lNorm)) return true;
         }
-        if (lang.autonym.toLowerCase().includes(rawLower)) return true;
+        const autoLower = lang.autonym.toLowerCase();
+        if (autoLower === rawLower) return true;
+        if (rawLower.length >= 4 && autoLower.includes(rawLower)) return true;
       }
       return false;
     };
@@ -10957,13 +11029,17 @@ var QueryBuilder = class _QueryBuilder {
   iso(code, includeAdditional = true) {
     const codeClean = code.trim().toLowerCase();
     const predicate = (v) => {
-      if (v.primaryLanguage.iso639_3.toLowerCase() === codeClean) {
+      const matchIso = (l) => {
+        if (l.iso639_3.toLowerCase() === codeClean) return true;
+        if (l.standards.iso639_3.part1?.toLowerCase() === codeClean) return true;
+        if (l.standards.bcp47.macrolanguage?.toLowerCase() === codeClean) return true;
+        return false;
+      };
+      if (matchIso(v.primaryLanguage)) {
         return true;
       }
       if (includeAdditional) {
-        return v.additionalLanguages.some(
-          (al) => al.iso639_3.toLowerCase() === codeClean
-        );
+        return v.additionalLanguages.some(matchIso);
       }
       return false;
     };
@@ -10975,10 +11051,13 @@ var QueryBuilder = class _QueryBuilder {
     const predicate = (v) => {
       for (const lang of v.allLanguages) {
         const lTag = lang.bcp47.toLowerCase();
+        const lIso = lang.iso639_3.toLowerCase();
+        const part1 = lang.standards.iso639_3.part1?.toLowerCase();
+        const macro = lang.standards.bcp47.macrolanguage?.toLowerCase();
         if (exact) {
-          if (lTag === tagClean) return true;
+          if (lTag === tagClean || lIso === tagClean || part1 === tagClean || macro === tagClean) return true;
         } else {
-          if (lTag === tagClean || lTag.startsWith(`${tagClean}-`)) return true;
+          if (lTag === tagClean || lTag.startsWith(`${tagClean}-`) || lIso === tagClean || part1 === tagClean || macro === tagClean) return true;
         }
       }
       return false;
@@ -66509,6 +66588,16 @@ var WikitonguesDB = class _WikitonguesDB {
   findByLanguage(languageQuery, includeAdditional = true) {
     return this.query().language(languageQuery, includeAdditional).all();
   }
+  /**
+   * Check if the database contains any video matching the language query
+   * (by ISO 639-3, ISO 639-1, BCP 47, macrolanguage, or name).
+   */
+  hasLanguage(query) {
+    const qClean = query.trim().toLowerCase();
+    if (this.index.byIso.has(qClean)) return true;
+    if (this.index.byBcp47.has(qClean)) return true;
+    return this.findByLanguage(query).length > 0;
+  }
   /**
    * Shortcut method to filter videos by common criteria.
    */