@lde/search 0.27.2 → 0.28.1

package/dist/adapter.d.ts

@@ -9,6 +9,7 @@
 export { assertTypeInSchema, physicalFields, irAlias, displayFieldName, displayFieldPattern, displayLangOf, searchableFields, facetableFields, filterableFields, sortableFields, outputFields, isInternalField, isInlineReference, nestedReferenceType, nestedFieldName, localLookupTypeOf, identityFieldOf, identityFieldName, referenceFields, referenceTypeNamed, rootTypeNamed, inlineFramingDepth, fieldNamed, datasetField, ID_FIELD, AND_KEY, OR_KEY, labelFieldOf, labelFieldNameOf, labelSourceNameOf, labelTargetNameOf, documentKeyOf, DEFAULT_LABEL_FIELD, isRangeFacet, isAbsoluteIri, isoToUnixSeconds, unixSecondsToIso, } from './schema.js';
 export type { PhysicalFields } from './schema.js';
 export { physicalNameTokens } from './physical-name.js';
+export { matchLanguage } from './language.js';
 export { joinGraph, MAX_JOIN_DEPTH } from './join-graph.js';
 export type { JoinGraph } from './join-graph.js';
 export { filterOperatorFor, filterOperator, filterOn, isWelded, isUnsatisfiable, validateQuery, assertValidQuery, resolvePath, pageForOffset, } from './query.js';

package/dist/adapter.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,EACL,kBAAkB,EAClB,cAAc,EACd,OAAO,EACP,gBAAgB,EAChB,mBAAmB,EACnB,aAAa,EACb,gBAAgB,EAChB,eAAe,EACf,gBAAgB,EAChB,cAAc,EACd,YAAY,EACZ,eAAe,EACf,iBAAiB,EACjB,mBAAmB,EACnB,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,kBAAkB,EAClB,aAAa,EACb,kBAAkB,EAClB,UAAU,EACV,YAAY,EACZ,QAAQ,EACR,OAAO,EACP,MAAM,EACN,YAAY,EACZ,gBAAgB,EAChB,iBAAiB,EACjB,iBAAiB,EACjB,aAAa,EACb,mBAAmB,EACnB,YAAY,EACZ,aAAa,EACb,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,aAAa,CAAC;AACrB,YAAY,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAClD,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAC;AACxD,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAC5D,YAAY,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,EACL,iBAAiB,EACjB,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,eAAe,EACf,aAAa,EACb,gBAAgB,EAChB,WAAW,EACX,aAAa,GACd,MAAM,YAAY,CAAC;AACpB,YAAY,EACV,cAAc,EACd,UAAU,EACV,YAAY,EACZ,WAAW,GACZ,MAAM,YAAY,CAAC"}
+{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../src/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,EACL,kBAAkB,EAClB,cAAc,EACd,OAAO,EACP,gBAAgB,EAChB,mBAAmB,EACnB,aAAa,EACb,gBAAgB,EAChB,eAAe,EACf,gBAAgB,EAChB,cAAc,EACd,YAAY,EACZ,eAAe,EACf,iBAAiB,EACjB,mBAAmB,EACnB,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,iBAAiB,EACjB,eAAe,EACf,kBAAkB,EAClB,aAAa,EACb,kBAAkB,EAClB,UAAU,EACV,YAAY,EACZ,QAAQ,EACR,OAAO,EACP,MAAM,EACN,YAAY,EACZ,gBAAgB,EAChB,iBAAiB,EACjB,iBAAiB,EACjB,aAAa,EACb,mBAAmB,EACnB,YAAY,EACZ,aAAa,EACb,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,aAAa,CAAC;AACrB,YAAY,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAClD,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAC;AACxD,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAC5D,YAAY,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,EACL,iBAAiB,EACjB,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,eAAe,EACf,aAAa,EACb,gBAAgB,EAChB,WAAW,EACX,aAAa,GACd,MAAM,YAAY,CAAC;AACpB,YAAY,EACV,cAAc,EACd,UAAU,EACV,YAAY,EACZ,WAAW,GACZ,MAAM,YAAY,CAAC"}

package/dist/adapter.js

@@ -8,5 +8,6 @@
  */
 export { assertTypeInSchema, physicalFields, irAlias, displayFieldName, displayFieldPattern, displayLangOf, searchableFields, facetableFields, filterableFields, sortableFields, outputFields, isInternalField, isInlineReference, nestedReferenceType, nestedFieldName, localLookupTypeOf, identityFieldOf, identityFieldName, referenceFields, referenceTypeNamed, rootTypeNamed, inlineFramingDepth, fieldNamed, datasetField, ID_FIELD, AND_KEY, OR_KEY, labelFieldOf, labelFieldNameOf, labelSourceNameOf, labelTargetNameOf, documentKeyOf, DEFAULT_LABEL_FIELD, isRangeFacet, isAbsoluteIri, isoToUnixSeconds, unixSecondsToIso, } from './schema.js';
 export { physicalNameTokens } from './physical-name.js';
+export { matchLanguage } from './language.js';
 export { joinGraph, MAX_JOIN_DEPTH } from './join-graph.js';
 export { filterOperatorFor, filterOperator, filterOn, isWelded, isUnsatisfiable, validateQuery, assertValidQuery, resolvePath, pageForOffset, } from './query.js';

package/dist/frame-by-type.d.ts

@@ -14,11 +14,16 @@ export interface SubjectIndex {
 }
 /**
  * Iterate `quads` once, grouping each subject’s triples. Duplicate triples are
- * collapsed here because some SPARQL engines (e.g. QLever) do not deduplicate
- * CONSTRUCT output. The source is consumed a single time, so it may be a
- * one-shot iterable (a generator chaining several sources); the whole subject
- * index is held, but never more than that plus one framed subgraph at a time
- * downstream.
+ * collapsed here: some SPARQL engines (e.g. QLever) do not deduplicate
+ * CONSTRUCT output, and a batch merges several readers’ output unfiltered.
+ * Framing would fold a repeated plain value on its own, but not a repeated
+ * RDF list cell (it then frames as raw `rdf:first`/`rdf:rest`), and without the
+ * set the index and every framed subgraph would grow with the duplication
+ * factor rather than with the distinct triples.
+ *
+ * The source is consumed a single time, so it may be a one-shot iterable (a
+ * generator chaining several sources); the whole subject index is held, but
+ * never more than that plus one framed subgraph at a time downstream.
  *
  * Roots are never discovered here – the caller ({@link projectRoots}, from the
  * pipeline selector) already holds them and passes them to {@link frameSubjects}

package/dist/frame-by-type.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"frame-by-type.d.ts","sourceRoot":"","sources":["../src/frame-by-type.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAGzC,4EAA4E;AAC5E,MAAM,MAAM,UAAU,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAIjD;;;;;;GAMG;AACH,MAAM,WAAW,YAAY;IAC3B,4EAA4E;IAC5E,QAAQ,CAAC,SAAS,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,IAAI,EAAE,CAAC,CAAC;CAC1D;AAED;;;;;;;;;;;GAWG;AACH,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,GAAG,YAAY,CAkBrE;AAED;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,wBAAuB,aAAa,CAClC,KAAK,EAAE,YAAY,EACnB,KAAK,EAAE,SAAS,MAAM,EAAE,EACxB,KAAK,SAAI,GACR,aAAa,CAAC,UAAU,CAAC,CAyB3B"}
+{"version":3,"file":"frame-by-type.d.ts","sourceRoot":"","sources":["../src/frame-by-type.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAGzC,4EAA4E;AAC5E,MAAM,MAAM,UAAU,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAIjD;;;;;;GAMG;AACH,MAAM,WAAW,YAAY;IAC3B,4EAA4E;IAC5E,QAAQ,CAAC,SAAS,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,IAAI,EAAE,CAAC,CAAC;CAC1D;AAED;;;;;;;;;;;;;;;;GAgBG;AACH,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,GAAG,YAAY,CAkBrE;AAED;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,wBAAuB,aAAa,CAClC,KAAK,EAAE,YAAY,EACnB,KAAK,EAAE,SAAS,MAAM,EAAE,EACxB,KAAK,SAAI,GACR,aAAa,CAAC,UAAU,CAAC,CAyB3B"}

package/dist/frame-by-type.js

@@ -2,11 +2,16 @@ import jsonld from 'jsonld';
 const FRAME_OPTIONS = { omitGraph: false, embed: '@always' };
 /**
  * Iterate `quads` once, grouping each subject’s triples. Duplicate triples are
- * collapsed here because some SPARQL engines (e.g. QLever) do not deduplicate
- * CONSTRUCT output. The source is consumed a single time, so it may be a
- * one-shot iterable (a generator chaining several sources); the whole subject
- * index is held, but never more than that plus one framed subgraph at a time
- * downstream.
+ * collapsed here: some SPARQL engines (e.g. QLever) do not deduplicate
+ * CONSTRUCT output, and a batch merges several readers’ output unfiltered.
+ * Framing would fold a repeated plain value on its own, but not a repeated
+ * RDF list cell (it then frames as raw `rdf:first`/`rdf:rest`), and without the
+ * set the index and every framed subgraph would grow with the duplication
+ * factor rather than with the distinct triples.
+ *
+ * The source is consumed a single time, so it may be a one-shot iterable (a
+ * generator chaining several sources); the whole subject index is held, but
+ * never more than that plus one framed subgraph at a time downstream.
  *
  * Roots are never discovered here – the caller ({@link projectRoots}, from the
  * pipeline selector) already holds them and passes them to {@link frameSubjects}

package/dist/language.d.ts

@@ -0,0 +1,22 @@
+/**
+ * The entries of `candidates` that language tag `tag` matches, best first, as
+ * the entries themselves (so a caller can index back into `candidates`).
+ *
+ * Tags are compared per BCP-47 subtag and case-insensitively, as language
+ * ranges (RFC 4647). A candidate matches when it shares the tag’s primary
+ * language, ranked:
+ *
+ * 1. the exact tag (`nl-NL` for `nl-NL`);
+ * 2. the tag’s truncations, most specific first – RFC 4647 lookup, so a
+ *    request for `nl-NL` finds a declared `nl`;
+ * 3. the tags it is a prefix of, in `candidates` order – RFC 4647 basic
+ *    filtering, so a range `nl` finds `nl-NL` and `nl-BE`;
+ * 4. the remaining tags of the same language, longest shared prefix first, so
+ *    a request for `nl-NL` still finds `nl-BE` rather than another language.
+ *
+ * The exact match therefore still wins where a general and a specific tag sit
+ * side by side (`en` and `en-GB`). `und`, the untagged bucket, matches nothing
+ * but `und`.
+ */
+export declare function matchLanguage(tag: string, candidates: readonly string[]): string[];
+//# sourceMappingURL=language.d.ts.map

package/dist/language.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"language.d.ts","sourceRoot":"","sources":["../src/language.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AACH,wBAAgB,aAAa,CAC3B,GAAG,EAAE,MAAM,EACX,UAAU,EAAE,SAAS,MAAM,EAAE,GAC5B,MAAM,EAAE,CA4BV"}

package/dist/language.js

@@ -0,0 +1,54 @@
+/**
+ * The entries of `candidates` that language tag `tag` matches, best first, as
+ * the entries themselves (so a caller can index back into `candidates`).
+ *
+ * Tags are compared per BCP-47 subtag and case-insensitively, as language
+ * ranges (RFC 4647). A candidate matches when it shares the tag’s primary
+ * language, ranked:
+ *
+ * 1. the exact tag (`nl-NL` for `nl-NL`);
+ * 2. the tag’s truncations, most specific first – RFC 4647 lookup, so a
+ *    request for `nl-NL` finds a declared `nl`;
+ * 3. the tags it is a prefix of, in `candidates` order – RFC 4647 basic
+ *    filtering, so a range `nl` finds `nl-NL` and `nl-BE`;
+ * 4. the remaining tags of the same language, longest shared prefix first, so
+ *    a request for `nl-NL` still finds `nl-BE` rather than another language.
+ *
+ * The exact match therefore still wins where a general and a specific tag sit
+ * side by side (`en` and `en-GB`). `und`, the untagged bucket, matches nothing
+ * but `und`.
+ */
+export function matchLanguage(tag, candidates) {
+    const subtags = tag.toLowerCase().split('-');
+    const ranked = [];
+    for (const candidate of candidates) {
+        const candidateSubtags = candidate.toLowerCase().split('-');
+        const shared = sharedPrefixLength(subtags, candidateSubtags);
+        const exact = shared === subtags.length && shared === candidateSubtags.length;
+        if (shared === 0 || (subtags[0] === 'und' && !exact)) {
+            continue;
+        }
+        const kind = exact
+            ? 0
+            : shared === candidateSubtags.length
+                ? 1
+                : shared === subtags.length
+                    ? 2
+                    : 3;
+        // Extensions keep candidate order; truncations and siblings rank by how
+        // much of the tag they share.
+        ranked.push({ candidate, kind, closeness: kind === 2 ? 0 : shared });
+    }
+    return ranked
+        .sort((left, right) => left.kind - right.kind || right.closeness - left.closeness)
+        .map(({ candidate }) => candidate);
+}
+function sharedPrefixLength(left, right) {
+    let length = 0;
+    while (length < left.length &&
+        length < right.length &&
+        left[length] === right[length]) {
+        length++;
+    }
+    return length;
+}

package/dist/project.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"project.d.ts","sourceRoot":"","sources":["../src/project.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAEzC,OAAO,EAGL,KAAK,UAAU,EAChB,MAAM,oBAAoB,CAAC;AAC5B,OAAO,EAkBL,KAAK,eAAe,EAEpB,KAAK,QAAQ,EAEb,KAAK,YAAY,EACjB,KAAK,UAAU,EAEhB,MAAM,aAAa,CAAC;AAErB;;;;;;GAMG;AACH,MAAM,MAAM,aAAa,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAEpD,+DAA+D;AAC/D,MAAM,MAAM,cAAc,GAAG;IAAE,EAAE,EAAE,MAAM,CAAA;CAAE,GAAG,aAAa,CAAC;AAE5D;;;;;;;;;;GAUG;AACH,MAAM,WAAW,iBAAkB,SAAQ,OAAO,CAChD,QAAQ,CAAC,MAAM,CAAC,eAAe,EAAE,MAAM,CAAC,CAAC,CAC1C;IACC,4CAA4C;IAC5C,QAAQ,CAAC,OAAO,CAAC,EAAE,MAAM,CAAC;CAC3B;AAKD;;;;;;;;;;;;;GAaG;AACH,wBAAgB,eAAe,CAC7B,IAAI,EAAE,UAAU,EAChB,UAAU,EAAE,UAAU,EACtB,MAAM,CAAC,EAAE,YAAY,EACrB,OAAO,GAAE,iBAAyC,GACjD,cAAc,CAgBhB;AAwKD;;;;;;;;;;;;GAYG;AACH,wBAAuB,YAAY,CACjC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,EACrB,KAAK,EAAE,SAAS,MAAM,EAAE,EACxB,MAAM,EAAE,YAAY,EACpB,UAAU,EAAE,QAAQ,EACpB,OAAO,GAAE,iBAAyC,GACjD,aAAa,CAAC,cAAc,CAAC,CAc/B"}
+{"version":3,"file":"project.d.ts","sourceRoot":"","sources":["../src/project.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAGzC,OAAO,EAGL,KAAK,UAAU,EAChB,MAAM,oBAAoB,CAAC;AAC5B,OAAO,EAkBL,KAAK,eAAe,EAEpB,KAAK,QAAQ,EAEb,KAAK,YAAY,EACjB,KAAK,UAAU,EAEhB,MAAM,aAAa,CAAC;AAErB;;;;;;GAMG;AACH,MAAM,MAAM,aAAa,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAEpD,+DAA+D;AAC/D,MAAM,MAAM,cAAc,GAAG;IAAE,EAAE,EAAE,MAAM,CAAA;CAAE,GAAG,aAAa,CAAC;AAE5D;;;;;;;;;;GAUG;AACH,MAAM,WAAW,iBAAkB,SAAQ,OAAO,CAChD,QAAQ,CAAC,MAAM,CAAC,eAAe,EAAE,MAAM,CAAC,CAAC,CAC1C;IACC,4CAA4C;IAC5C,QAAQ,CAAC,OAAO,CAAC,EAAE,MAAM,CAAC;CAC3B;AAKD;;;;;;;;;;;;;GAaG;AACH,wBAAgB,eAAe,CAC7B,IAAI,EAAE,UAAU,EAChB,UAAU,EAAE,UAAU,EACtB,MAAM,CAAC,EAAE,YAAY,EACrB,OAAO,GAAE,iBAAyC,GACjD,cAAc,CAgBhB;AAwKD;;;;;;;;;;;;GAYG;AACH,wBAAuB,YAAY,CACjC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,EACrB,KAAK,EAAE,SAAS,MAAM,EAAE,EACxB,MAAM,EAAE,YAAY,EACpB,UAAU,EAAE,QAAQ,EACpB,OAAO,GAAE,iBAAyC,GACjD,aAAa,CAAC,cAAc,CAAC,CAc/B"}

package/dist/project.js

@@ -1,4 +1,5 @@
 import { fold } from '@lde/text-normalization';
+import { matchLanguage } from './language.js';
 import { buildSubjectIndex, frameSubjects, } from './frame-by-type.js';
 import { assertTypeInSchema, displayFieldName, documentKeyOf, fieldNamed, inheritedFacetKeys, inlineFramingDepth, irAlias, isAbsoluteIri, isInternalField, isInlineReference, isoToUnixSeconds, labelSourceNameOf, localLookupTypeOf, physicalFields, referenceTypeNamed, rootTypeNamed, } from './schema.js';
 /** The context a projection runs with when its caller supplied none. */
@@ -391,9 +392,36 @@ function applyText(document, values, field) {
     // here it simply indexes nothing.
     if (field.searchable !== undefined || field.sortable === true) {
         const names = physicalFields(field);
-        const valuesPerLocale = field.locales.map((locale) => values
-            .filter((value) => value.lang === locale)
-            .map((value) => value.value));
+        // A literal lands under the declared locale its tag best matches as a
+        // language range, so `nl-NL` titles are keyed under a declared `nl`; within
+        // a locale, the exact tag comes first.
+        const valuesPerLanguage = new Map();
+        for (const { lang, value } of values) {
+            const languageValues = valuesPerLanguage.get(lang);
+            if (languageValues === undefined) {
+                valuesPerLanguage.set(lang, [value]);
+            }
+            else {
+                languageValues.push(value);
+            }
+        }
+        const languagesPerLocale = new Map();
+        for (const entry of valuesPerLanguage) {
+            const locale = matchLanguage(entry[0], field.locales)[0];
+            if (locale !== undefined) {
+                languagesPerLocale.set(locale, [
+                    ...(languagesPerLocale.get(locale) ?? []),
+                    entry,
+                ]);
+            }
+        }
+        const valuesPerLocale = field.locales.map((locale) => {
+            const entries = languagesPerLocale.get(locale) ?? [];
+            const ranked = matchLanguage(locale, entries.map(([language]) => language));
+            return entries
+                .sort(([left], [right]) => ranked.indexOf(left) - ranked.indexOf(right))
+                .flatMap(([, languageValues]) => languageValues);
+        });
         // What every locale’s sort key falls back to: the document’s first value
         // in `locales` order, which is the declaration’s own statement of which
         // language stands in for the others.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lde/search",
-  "version": "0.27.2",
+  "version": "0.28.1",
   "description": "Engine- and domain-agnostic core for RDF-backed search: a unified declarative field model (SearchField/SearchType/SearchSchema), a neutral query IR, the SearchEngine port with logical result types, and a streaming CONSTRUCT-to-document projection. Bakes in no engine, protocol, or domain.",
   "repository": {
     "url": "git+https://github.com/ldelements/lde.git",
@@ -43,7 +43,7 @@
     "!**/*.tsbuildinfo"
   ],
   "dependencies": {
-    "@lde/text-normalization": "^0.1.3",
+    "@lde/text-normalization": "^0.2.0",
     "@rdfjs/types": "^2.0.1",
     "inflection": "^3.0.2",
     "jsonld": "^9.0.0",