@lde/pipeline-void 0.2.31 → 0.2.32

package/README.md

@@ -9,10 +9,10 @@ VOiD (Vocabulary of Interlinked Datasets) statistical analysis for RDF datasets.
 - `createLanguageStage(distribution)` — Per-class language tags
 - `createObjectClassStage(distribution)` — Per-class object class partitions
 
-## Streaming transformers
+## Executor decorators
 
-- `withVocabularies(quads, datasetIri)` — Detect and append `void:vocabulary` triples
-- `withProvenance(quads, iri, startedAt, endedAt)` — Append PROV-O provenance metadata
+- `VocabularyExecutor` — Wraps an executor; detects and appends `void:vocabulary` triples
+- `ProvenanceExecutor` — Wraps an executor; appends PROV-O provenance metadata with automatic timing
 
 ## SPARQL Queries
 
@@ -43,20 +43,23 @@ Generic VOiD analysis queries included:
 import {
   createQueryStage,
   createDatatypeStage,
-  withVocabularies,
-  withProvenance,
+  VocabularyExecutor,
+  Stage,
 } from '@lde/pipeline-void';
-import { Distribution } from '@lde/dataset';
-
-const distribution = Distribution.sparql(new URL('http://example.com/sparql'));
+import { SparqlConstructExecutor } from '@lde/pipeline';
 
 // Simple CONSTRUCT query stage
-const stage = await createQueryStage('triples.rq', distribution);
+const stage = await createQueryStage('triples.rq');
 await stage.run(dataset, distribution, writer);
 
-// Per-class stage (streaming)
-const datatypeStage = await createDatatypeStage(distribution);
-await datatypeStage.run(dataset, distribution, writer);
+// Executor decorator: vocabulary detection wraps entity-properties executor
+const executor = await SparqlConstructExecutor.fromFile(
+  'queries/entity-properties.rq',
+);
+const entityPropertiesStage = new Stage({
+  name: 'entity-properties',
+  executors: new VocabularyExecutor(executor),
+});
 ```
 
 ## Validation

package/dist/provenance.d.ts

@@ -1,14 +1,23 @@
+import { Dataset, Distribution } from '@lde/dataset';
+import { NotSupported, type Executor, type ExecuteOptions } from '@lde/pipeline';
 import type { Quad } from '@rdfjs/types';
 /**
- * Streaming transformer that passes through all quads and appends
- * PROV-O provenance metadata.
+ * Executor decorator that passes through all quads from the inner executor
+ * and appends PROV-O provenance metadata.
+ *
+ * Timestamps are captured automatically: `startedAt` when `execute()` is
+ * called, `endedAt` when the inner quad stream is fully consumed.
  *
  * Appended quads:
- * - `<iri> a prov:Entity`
- * - `<iri> prov:wasGeneratedBy _:activity`
+ * - `<dataset> a prov:Entity`
+ * - `<dataset> prov:wasGeneratedBy _:activity`
  * - `_:activity a prov:Activity`
  * - `_:activity prov:startedAtTime "..."^^xsd:dateTime`
  * - `_:activity prov:endedAtTime "..."^^xsd:dateTime`
  */
-export declare function withProvenance(quads: AsyncIterable<Quad>, iri: string, startedAt: Date, endedAt: Date): AsyncIterable<Quad>;
+export declare class ProvenanceExecutor implements Executor {
+    private readonly inner;
+    constructor(inner: Executor);
+    execute(dataset: Dataset, distribution: Distribution, options?: ExecuteOptions): Promise<AsyncIterable<Quad> | NotSupported>;
+}
 //# sourceMappingURL=provenance.d.ts.map

package/dist/provenance.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"provenance.d.ts","sourceRoot":"","sources":["../src/provenance.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAiBzC;;;;;;;;;;GAUG;AACH,wBAAuB,cAAc,CACnC,KAAK,EAAE,aAAa,CAAC,IAAI,CAAC,EAC1B,GAAG,EAAE,MAAM,EACX,SAAS,EAAE,IAAI,EACf,OAAO,EAAE,IAAI,GACZ,aAAa,CAAC,IAAI,CAAC,CAqBrB"}
+{"version":3,"file":"provenance.d.ts","sourceRoot":"","sources":["../src/provenance.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACrD,OAAO,EACL,YAAY,EACZ,KAAK,QAAQ,EACb,KAAK,cAAc,EACpB,MAAM,eAAe,CAAC;AACvB,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAiBzC;;;;;;;;;;;;;GAaG;AACH,qBAAa,kBAAmB,YAAW,QAAQ;IACrC,OAAO,CAAC,QAAQ,CAAC,KAAK;gBAAL,KAAK,EAAE,QAAQ;IAEtC,OAAO,CACX,OAAO,EAAE,OAAO,EAChB,YAAY,EAAE,YAAY,EAC1B,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,aAAa,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC;CAQ/C"}

package/dist/provenance.js

@@ -1,3 +1,4 @@
+import { NotSupported, } from '@lde/pipeline';
 import { DataFactory } from 'n3';
 const { namedNode, literal, blankNode, quad } = DataFactory;
 const RDF_TYPE = namedNode('http://www.w3.org/1999/02/22-rdf-syntax-ns#type');
@@ -8,20 +9,38 @@ const PROV_STARTED_AT_TIME = namedNode('http://www.w3.org/ns/prov#startedAtTime'
 const PROV_ENDED_AT_TIME = namedNode('http://www.w3.org/ns/prov#endedAtTime');
 const XSD_DATE_TIME = namedNode('http://www.w3.org/2001/XMLSchema#dateTime');
 /**
- * Streaming transformer that passes through all quads and appends
- * PROV-O provenance metadata.
+ * Executor decorator that passes through all quads from the inner executor
+ * and appends PROV-O provenance metadata.
+ *
+ * Timestamps are captured automatically: `startedAt` when `execute()` is
+ * called, `endedAt` when the inner quad stream is fully consumed.
  *
  * Appended quads:
- * - `<iri> a prov:Entity`
- * - `<iri> prov:wasGeneratedBy _:activity`
+ * - `<dataset> a prov:Entity`
+ * - `<dataset> prov:wasGeneratedBy _:activity`
  * - `_:activity a prov:Activity`
  * - `_:activity prov:startedAtTime "..."^^xsd:dateTime`
  * - `_:activity prov:endedAtTime "..."^^xsd:dateTime`
  */
-export async function* withProvenance(quads, iri, startedAt, endedAt) {
+export class ProvenanceExecutor {
+    inner;
+    constructor(inner) {
+        this.inner = inner;
+    }
+    async execute(dataset, distribution, options) {
+        const startedAt = new Date();
+        const result = await this.inner.execute(dataset, distribution, options);
+        if (result instanceof NotSupported) {
+            return result;
+        }
+        return withProvenance(result, dataset.iri.toString(), startedAt);
+    }
+}
+async function* withProvenance(quads, iri, startedAt) {
     for await (const q of quads) {
         yield q;
     }
+    const endedAt = new Date();
     const subject = namedNode(iri);
     const activity = blankNode();
     yield quad(subject, RDF_TYPE, PROV_ENTITY);

package/dist/vocabularyAnalyzer.d.ts

@@ -1,11 +1,18 @@
+import { Dataset, Distribution } from '@lde/dataset';
+import { NotSupported, type Executor, type ExecuteOptions } from '@lde/pipeline';
 import type { Quad } from '@rdfjs/types';
 /**
- * Streaming transformer that passes through all quads and appends
- * `void:vocabulary` triples for detected vocabulary prefixes.
+ * Executor decorator that passes through all quads from the inner executor
+ * and appends `void:vocabulary` triples for detected vocabulary prefixes.
  *
  * Inspects quads with predicate `void:property` to detect known vocabulary
  * namespace prefixes, then yields the corresponding `void:vocabulary` quads
- * after all input quads have been consumed.
+ * after all inner quads have been consumed.
  */
-export declare function withVocabularies(quads: AsyncIterable<Quad>, datasetIri: string, vocabularies?: readonly string[]): AsyncIterable<Quad>;
+export declare class VocabularyExecutor implements Executor {
+    private readonly inner;
+    private readonly vocabularies;
+    constructor(inner: Executor, vocabularies?: readonly string[]);
+    execute(dataset: Dataset, distribution: Distribution, options?: ExecuteOptions): Promise<AsyncIterable<Quad> | NotSupported>;
+}
 //# sourceMappingURL=vocabularyAnalyzer.d.ts.map

package/dist/vocabularyAnalyzer.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"vocabularyAnalyzer.d.ts","sourceRoot":"","sources":["../src/vocabularyAnalyzer.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAczC;;;;;;;GAOG;AACH,wBAAuB,gBAAgB,CACrC,KAAK,EAAE,aAAa,CAAC,IAAI,CAAC,EAC1B,UAAU,EAAE,MAAM,EAClB,YAAY,GAAE,SAAS,MAAM,EAAwB,GACpD,aAAa,CAAC,IAAI,CAAC,CAqBrB"}
+{"version":3,"file":"vocabularyAnalyzer.d.ts","sourceRoot":"","sources":["../src/vocabularyAnalyzer.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACrD,OAAO,EACL,YAAY,EACZ,KAAK,QAAQ,EACb,KAAK,cAAc,EACpB,MAAM,eAAe,CAAC;AACvB,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,cAAc,CAAC;AAczC;;;;;;;GAOG;AACH,qBAAa,kBAAmB,YAAW,QAAQ;IAE/C,OAAO,CAAC,QAAQ,CAAC,KAAK;IACtB,OAAO,CAAC,QAAQ,CAAC,YAAY;gBADZ,KAAK,EAAE,QAAQ,EACf,YAAY,GAAE,SAAS,MAAM,EAAwB;IAGlE,OAAO,CACX,OAAO,EAAE,OAAO,EAChB,YAAY,EAAE,YAAY,EAC1B,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,aAAa,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC;CAO/C"}

package/dist/vocabularyAnalyzer.js

@@ -1,3 +1,4 @@
+import { NotSupported, } from '@lde/pipeline';
 import prefixes from '@zazuko/prefixes';
 import { DataFactory } from 'n3';
 const { namedNode, quad } = DataFactory;
@@ -8,14 +9,29 @@ const defaultVocabularies = [
     ...new Set(Object.values(prefixes)),
 ];
 /**
- * Streaming transformer that passes through all quads and appends
- * `void:vocabulary` triples for detected vocabulary prefixes.
+ * Executor decorator that passes through all quads from the inner executor
+ * and appends `void:vocabulary` triples for detected vocabulary prefixes.
  *
  * Inspects quads with predicate `void:property` to detect known vocabulary
  * namespace prefixes, then yields the corresponding `void:vocabulary` quads
- * after all input quads have been consumed.
+ * after all inner quads have been consumed.
  */
-export async function* withVocabularies(quads, datasetIri, vocabularies = defaultVocabularies) {
+export class VocabularyExecutor {
+    inner;
+    vocabularies;
+    constructor(inner, vocabularies = defaultVocabularies) {
+        this.inner = inner;
+        this.vocabularies = vocabularies;
+    }
+    async execute(dataset, distribution, options) {
+        const result = await this.inner.execute(dataset, distribution, options);
+        if (result instanceof NotSupported) {
+            return result;
+        }
+        return withVocabularies(result, dataset.iri.toString(), this.vocabularies);
+    }
+}
+async function* withVocabularies(quads, datasetIri, vocabularies) {
     const detectedVocabularies = new Set();
     for await (const q of quads) {
         yield q;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lde/pipeline-void",
-  "version": "0.2.31",
+  "version": "0.2.32",
   "description": "VOiD (Vocabulary of Interlinked Datasets) statistical analysis for RDF datasets",
   "repository": {
     "url": "https://github.com/ldengine/lde",
@@ -24,6 +24,7 @@
     "!**/*.tsbuildinfo"
   ],
   "dependencies": {
+    "@lde/dataset": "0.6.9",
     "@lde/pipeline": "0.6.28",
     "@rdfjs/types": "^2.0.1",
     "@zazuko/prefixes": "^2.6.1",