@lde/search 0.4.1 → 0.5.0

package/README.md

@@ -150,8 +150,14 @@ const DATASET = defineSearchType({
   ],
 });
 
-for await (const document of projectGraph(quads, searchSchema(DATASET))) {
-  // one flat search document per matching subject, streamed
+for await (const { searchType, document } of projectGraph(
+  quads,
+  searchSchema(DATASET),
+)) {
+  // one flat search document per matching subject, streamed and tagged with the
+  // SearchType it was framed from — so a multi-collection writer can route each
+  // document to the collection for its type. A single-collection consumer just
+  // reads `document`.
 }
 ```
 
@@ -218,6 +224,12 @@ triples are collapsed first, because some SPARQL engines (e.g. QLever) do not
 deduplicate `CONSTRUCT` output. The IR carries no `@context`, so a `derive` function
 reading it sees full predicate IRIs with language tags preserved.
 
+Each yielded value is a `{ searchType, document }` pair: the whole schema
+projects into **one** mixed stream, and every document is tagged with the
+`SearchType` it was framed from. That tag is what lets the write side fan the
+stream out to per-type collections without re-deriving the type from the
+document — see `@lde/search-pipeline`’s multi-collection writer.
+
 `projectGraph` **consumes the quads once** – a single scan builds the subject
 index every type frames off – and so accepts any `Iterable<Quad>`, not just a
 materialized array. A caller merging several sources can pass a chained

package/dist/index.d.ts

@@ -1,5 +1,5 @@
 export { projectGraph, irisOf, literalsOf, firstLiteralOf } from './project.js';
-export type { SearchDocument } from './project.js';
+export type { SearchDocument, TypedSearchDocument } from './project.js';
 export { defineSearchType, searchSchema, validateSearchType, assertValidSearchType, } from './schema.js';
 export type { FieldKind, SearchField, SearchFieldBase, TextField, KeywordField, ReferenceField, NumericField, BooleanField, SearchType, SearchTypeIssue, SearchSchema, FacetRange, } from './schema.js';
 export type { SearchQuery, Filter, Sort } from './query.js';

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AASA,OAAO,EAAE,YAAY,EAAE,MAAM,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,cAAc,CAAC;AAChF,YAAY,EAAE,cAAc,EAAE,MAAM,cAAc,CAAC;AAKnD,OAAO,EACL,gBAAgB,EAChB,YAAY,EACZ,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,aAAa,CAAC;AACrB,YAAY,EACV,SAAS,EACT,WAAW,EACX,eAAe,EACf,SAAS,EACT,YAAY,EACZ,cAAc,EACd,YAAY,EACZ,YAAY,EACZ,UAAU,EACV,eAAe,EACf,YAAY,EACZ,UAAU,GACX,MAAM,aAAa,CAAC;AAIrB,YAAY,EAAE,WAAW,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAI5D,YAAY,EACV,YAAY,EACZ,YAAY,EACZ,SAAS,EACT,cAAc,EACd,WAAW,EACX,cAAc,EACd,SAAS,EACT,WAAW,EACX,QAAQ,EACR,aAAa,EACb,aAAa,EACb,cAAc,GACf,MAAM,aAAa,CAAC;AAErB,YAAY,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AASA,OAAO,EAAE,YAAY,EAAE,MAAM,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,cAAc,CAAC;AAChF,YAAY,EAAE,cAAc,EAAE,mBAAmB,EAAE,MAAM,cAAc,CAAC;AAKxE,OAAO,EACL,gBAAgB,EAChB,YAAY,EACZ,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,aAAa,CAAC;AACrB,YAAY,EACV,SAAS,EACT,WAAW,EACX,eAAe,EACf,SAAS,EACT,YAAY,EACZ,cAAc,EACd,YAAY,EACZ,YAAY,EACZ,UAAU,EACV,eAAe,EACf,YAAY,EACZ,UAAU,GACX,MAAM,aAAa,CAAC;AAIrB,YAAY,EAAE,WAAW,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,YAAY,CAAC;AAI5D,YAAY,EACV,YAAY,EACZ,YAAY,EACZ,SAAS,EACT,cAAc,EACd,WAAW,EACX,cAAc,EACd,SAAS,EACT,WAAW,EACX,QAAQ,EACR,aAAa,EACb,aAAa,EACb,cAAc,GACf,MAAM,aAAa,CAAC;AAErB,YAAY,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAC"}

package/dist/project.d.ts

@@ -5,6 +5,16 @@ import { type SearchSchema, type SearchType } from './schema.js';
 export type SearchDocument = {
     id: string;
 } & Record<string, unknown>;
+/**
+ * A projected document tagged with the {@link SearchType} it was projected
+ * from — one element of {@link projectGraph}’s mixed, whole-schema stream. The
+ * tag is what lets a multi-collection writer route each document to the
+ * collection for its type without re-deriving the type from the document.
+ */
+export interface TypedSearchDocument {
+    readonly searchType: SearchType;
+    readonly document: SearchDocument;
+}
 /**
  * Project one framed JSON-LD node into a flat search document: apply each field
  * of the type in declaration order. A field with a `derive` function computes
@@ -16,16 +26,19 @@ export type SearchDocument = {
 export declare function projectDocument(node: FramedNode, searchType: SearchType): SearchDocument;
 /**
  * Frame `quads` for every root type in the schema and project each node with its
- * type’s declaration — the multi-shape pipeline. Streams one document at a time
- * so memory stays flat. The IR maps to a declaration by type, so adding a shape
- * is adding a `SearchType` to the schema (no engine change).
+ * type’s declaration — the multi-shape pipeline. Yields each document tagged
+ * with its {@link SearchType} ({@link TypedSearchDocument}), so a downstream
+ * multi-collection writer can route it to that type’s collection; a
+ * single-collection consumer just reads `.document`. Streams one document at a
+ * time so memory stays flat. The IR maps to a declaration by type, so adding a
+ * shape is adding a `SearchType` to the schema (no engine change).
  *
  * Consumes `quads` once (a single scan builds the shared subject index that
  * every type frames off), so it accepts any `Iterable` – a materialized array or
  * a chained generator merging several sources (`function* () { yield* a; yield* b; }`)
  * with no intermediate copy at the projection peak.
  */
-export declare function projectGraph(quads: Iterable<Quad>, schema: SearchSchema): AsyncIterable<SearchDocument>;
+export declare function projectGraph(quads: Iterable<Quad>, schema: SearchSchema): AsyncIterable<TypedSearchDocument>;
 export declare function literalsOf(node: FramedNode, path: string): string[];
 export declare function firstLiteralOf(node: FramedNode, path: string): string | undefined;
 export declare function irisOf(node: FramedNode, path: string): string[];

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,EAML,KAAK,YAAY,EACjB,KAAK,UAAU,EAEhB,MAAM,aAAa,CAAC;AAErB,+DAA+D;AAC/D,MAAM,MAAM,cAAc,GAAG;IAAE,EAAE,EAAE,MAAM,CAAA;CAAE,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAEtE;;;;;;;GAOG;AACH,wBAAgB,eAAe,CAC7B,IAAI,EAAE,UAAU,EAChB,UAAU,EAAE,UAAU,GACrB,cAAc,CAYhB;AAED;;;;;;;;;;GAUG;AACH,wBAAuB,YAAY,CACjC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,EACrB,MAAM,EAAE,YAAY,GACnB,aAAa,CAAC,cAAc,CAAC,CAW/B;AAsID,wBAAgB,UAAU,CAAC,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAInE;AAED,wBAAgB,cAAc,CAC5B,IAAI,EAAE,UAAU,EAChB,IAAI,EAAE,MAAM,GACX,MAAM,GAAG,SAAS,CAEpB;AAED,wBAAgB,MAAM,CAAC,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAI/D"}
+{"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,EAML,KAAK,YAAY,EACjB,KAAK,UAAU,EAEhB,MAAM,aAAa,CAAC;AAErB,+DAA+D;AAC/D,MAAM,MAAM,cAAc,GAAG;IAAE,EAAE,EAAE,MAAM,CAAA;CAAE,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAEtE;;;;;GAKG;AACH,MAAM,WAAW,mBAAmB;IAClC,QAAQ,CAAC,UAAU,EAAE,UAAU,CAAC;IAChC,QAAQ,CAAC,QAAQ,EAAE,cAAc,CAAC;CACnC;AAED;;;;;;;GAOG;AACH,wBAAgB,eAAe,CAC7B,IAAI,EAAE,UAAU,EAChB,UAAU,EAAE,UAAU,GACrB,cAAc,CAYhB;AAED;;;;;;;;;;;;;GAaG;AACH,wBAAuB,YAAY,CACjC,KAAK,EAAE,QAAQ,CAAC,IAAI,CAAC,EACrB,MAAM,EAAE,YAAY,GACnB,aAAa,CAAC,mBAAmB,CAAC,CAWpC;AAsID,wBAAgB,UAAU,CAAC,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAInE;AAED,wBAAgB,cAAc,CAC5B,IAAI,EAAE,UAAU,EAChB,IAAI,EAAE,MAAM,GACX,MAAM,GAAG,SAAS,CAEpB;AAED,wBAAgB,MAAM,CAAC,IAAI,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,GAAG,MAAM,EAAE,CAI/D"}

package/dist/project.js

@@ -22,9 +22,12 @@ export function projectDocument(node, searchType) {
 }
 /**
  * Frame `quads` for every root type in the schema and project each node with its
- * type’s declaration — the multi-shape pipeline. Streams one document at a time
- * so memory stays flat. The IR maps to a declaration by type, so adding a shape
- * is adding a `SearchType` to the schema (no engine change).
+ * type’s declaration — the multi-shape pipeline. Yields each document tagged
+ * with its {@link SearchType} ({@link TypedSearchDocument}), so a downstream
+ * multi-collection writer can route it to that type’s collection; a
+ * single-collection consumer just reads `.document`. Streams one document at a
+ * time so memory stays flat. The IR maps to a declaration by type, so adding a
+ * shape is adding a `SearchType` to the schema (no engine change).
  *
  * Consumes `quads` once (a single scan builds the shared subject index that
  * every type frames off), so it accepts any `Iterable` – a materialized array or
@@ -36,7 +39,7 @@ export async function* projectGraph(quads, schema) {
     const index = buildSubjectIndex(quads, types.map((searchType) => searchType.type));
     for (const searchType of types) {
         for await (const node of frameSubjects(index, searchType.type)) {
-            yield projectDocument(node, searchType);
+            yield { searchType, document: projectDocument(node, searchType) };
         }
     }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lde/search",
-  "version": "0.4.1",
+  "version": "0.5.0",
   "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",