@lde/pipeline 0.28.6 → 0.28.8

package/README.md

@@ -229,21 +229,47 @@ Writes generated quads to a destination:
 
 Plugins hook into the pipeline lifecycle via the `PipelinePlugin` interface. Register them in the `plugins` array when constructing a `Pipeline`.
 
+#### `namespaceNormalizationPlugin(options)`
+
+Generic plugin that rewrites namespace prefixes in `void:class` and `void:property` quad objects. Accepts `from` and `to` options specifying the source and target namespace URI prefixes. `void:vocabulary` quads are left unchanged so consumers can see which namespace the source dataset actually uses.
+
+```typescript
+import { namespaceNormalizationPlugin } from ‘@lde/pipeline’;
+
+new Pipeline({
+  // ...
+  plugins: [
+    namespaceNormalizationPlugin({
+      from: ‘http://example.org/’,
+      to: ‘https://example.org/’,
+    }),
+  ],
+});
+```
+
 #### `provenancePlugin()`
 
 Appends [PROV-O](https://www.w3.org/TR/prov-o/) provenance quads (`prov:Entity`, `prov:Activity`, `prov:startedAtTime`, `prov:endedAtTime`) to every stage’s output.
 
-#### `schemaOrgNormalizationPlugin()`
+#### `schemaOrgNormalizationPlugin(options?)`
+
+Normalizes Schema.org namespace prefixes in `void:class` and `void:property` quad objects. By default, rewrites `http://schema.org/` to `https://schema.org/`. Pass `{ reverse: true }` to normalize in the opposite direction (`https://` to `http://`). `void:vocabulary` quads are left unchanged so consumers can see which namespace the source dataset actually uses.
 
-Normalizes `http://schema.org/` to `https://schema.org/` in `void:class` and `void:property` quad objects, so downstream consumers can rely on a single canonical namespace. `void:vocabulary` quads are left unchanged so consumers can see which namespace the source dataset actually uses.
+This is a convenience wrapper around `namespaceNormalizationPlugin`.
 
 ```typescript
-import { schemaOrgNormalizationPlugin, provenancePlugin } from '@lde/pipeline';
+import { schemaOrgNormalizationPlugin, provenancePlugin } from ‘@lde/pipeline’;
 
 new Pipeline({
   // ...
   plugins: [schemaOrgNormalizationPlugin(), provenancePlugin()],
 });
+
+// Or reverse: normalize https to http
+new Pipeline({
+  // ...
+  plugins: [schemaOrgNormalizationPlugin({reverse: true})],
+});
 ```
 
 ## Usage

package/dist/index.d.ts

@@ -9,6 +9,7 @@ export * from './stageOutputResolver.js';
 export * from './sparql/index.js';
 export * from './distribution/index.js';
 export * from './writer/index.js';
+export * from './plugin/namespaceNormalization.js';
 export * from './plugin/provenance.js';
 export * from './plugin/schemaOrgNormalization.js';
 //# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,gBAAgB,CAAC;AAC/B,cAAc,iBAAiB,CAAC;AAChC,cAAc,YAAY,CAAC;AAC3B,cAAc,eAAe,CAAC;AAC9B,cAAc,uBAAuB,CAAC;AACtC,cAAc,eAAe,CAAC;AAC9B,cAAc,YAAY,CAAC;AAC3B,cAAc,0BAA0B,CAAC;AACzC,cAAc,mBAAmB,CAAC;AAClC,cAAc,yBAAyB,CAAC;AACxC,cAAc,mBAAmB,CAAC;AAClC,cAAc,wBAAwB,CAAC;AACvC,cAAc,oCAAoC,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,gBAAgB,CAAC;AAC/B,cAAc,iBAAiB,CAAC;AAChC,cAAc,YAAY,CAAC;AAC3B,cAAc,eAAe,CAAC;AAC9B,cAAc,uBAAuB,CAAC;AACtC,cAAc,eAAe,CAAC;AAC9B,cAAc,YAAY,CAAC;AAC3B,cAAc,0BAA0B,CAAC;AACzC,cAAc,mBAAmB,CAAC;AAClC,cAAc,yBAAyB,CAAC;AACxC,cAAc,mBAAmB,CAAC;AAClC,cAAc,oCAAoC,CAAC;AACnD,cAAc,wBAAwB,CAAC;AACvC,cAAc,oCAAoC,CAAC"}

package/dist/index.js

@@ -9,5 +9,6 @@ export * from './stageOutputResolver.js';
 export * from './sparql/index.js';
 export * from './distribution/index.js';
 export * from './writer/index.js';
+export * from './plugin/namespaceNormalization.js';
 export * from './plugin/provenance.js';
 export * from './plugin/schemaOrgNormalization.js';

package/dist/pipeline.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../src/pipeline.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,eAAe,CAAC;AACrD,OAAO,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AACnC,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEjD,OAAO,EACL,KAAK,oBAAoB,EAE1B,MAAM,4BAA4B,CAAC;AAQpC,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,0BAA0B,CAAC;AACpE,OAAO,KAAK,EAEV,gBAAgB,EACjB,MAAM,uBAAuB,CAAC;AAE/B,wDAAwD;AACxD,MAAM,WAAW,cAAc;IAC7B,IAAI,EAAE,MAAM,CAAC;IACb,gDAAgD;IAChD,gBAAgB,CAAC,EAAE,aAAa,CAAC;CAClC;AAED,MAAM,WAAW,eAAe;IAC9B,eAAe,EAAE,eAAe,CAAC;IACjC,MAAM,EAAE,KAAK,EAAE,CAAC;IAChB,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IAC3B,OAAO,CAAC,EAAE,cAAc,EAAE,CAAC;IAC3B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,oBAAoB,CAAC,EAAE,oBAAoB,CAAC;IAC5C,QAAQ,CAAC,EAAE;QACT,mBAAmB,EAAE,mBAAmB,CAAC;QACzC,SAAS,EAAE,MAAM,CAAC;KACnB,CAAC;IACF,QAAQ,CAAC,EAAE,gBAAgB,CAAC;CAC7B;AAgED,qBAAa,QAAQ;IACnB,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAS;IAC9B,OAAO,CAAC,QAAQ,CAAC,eAAe,CAAkB;IAClD,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAU;IACjC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAS;IAChC,OAAO,CAAC,QAAQ,CAAC,oBAAoB,CAAuB;IAC5D,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAA8B;IACxD,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAmB;gBAEjC,OAAO,EAAE,eAAe;IAgC9B,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC;YAoBZ,cAAc;IAkE5B;;;OAGG;YACW,QAAQ;IA6CtB,2EAA2E;YAC7D,eAAe;YAcf,QAAQ;YAmDP,SAAS;CAczB"}
+{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../src/pipeline.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,eAAe,CAAC;AACrD,OAAO,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AACnC,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEjD,OAAO,EACL,KAAK,oBAAoB,EAE1B,MAAM,4BAA4B,CAAC;AAQpC,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,0BAA0B,CAAC;AACpE,OAAO,KAAK,EAEV,gBAAgB,EACjB,MAAM,uBAAuB,CAAC;AAE/B,wDAAwD;AACxD,MAAM,WAAW,cAAc;IAC7B,IAAI,EAAE,MAAM,CAAC;IACb,gDAAgD;IAChD,gBAAgB,CAAC,EAAE,aAAa,CAAC;CAClC;AAED,MAAM,WAAW,eAAe;IAC9B,eAAe,EAAE,eAAe,CAAC;IACjC,MAAM,EAAE,KAAK,EAAE,CAAC;IAChB,OAAO,EAAE,MAAM,GAAG,MAAM,EAAE,CAAC;IAC3B,OAAO,CAAC,EAAE,cAAc,EAAE,CAAC;IAC3B,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,oBAAoB,CAAC,EAAE,oBAAoB,CAAC;IAC5C,QAAQ,CAAC,EAAE;QACT,mBAAmB,EAAE,mBAAmB,CAAC;QACzC,SAAS,EAAE,MAAM,CAAC;KACnB,CAAC;IACF,QAAQ,CAAC,EAAE,gBAAgB,CAAC;CAC7B;AAgFD,qBAAa,QAAQ;IACnB,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAS;IAC9B,OAAO,CAAC,QAAQ,CAAC,eAAe,CAAkB;IAClD,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAU;IACjC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAS;IAChC,OAAO,CAAC,QAAQ,CAAC,oBAAoB,CAAuB;IAC5D,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAA8B;IACxD,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAmB;gBAEjC,OAAO,EAAE,eAAe;IAgC9B,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC;YAoBZ,cAAc;IAkE5B;;;OAGG;YACW,QAAQ;IA6CtB,2EAA2E;YAC7D,eAAe;YAcf,QAAQ;YAmDP,SAAS;CAczB"}

package/dist/pipeline.js

@@ -7,26 +7,37 @@ import { NetworkError, SparqlProbeResult, } from './distribution/probe.js';
 import { NotSupported } from './sparql/executor.js';
 /**
  * Split an async iterable into `count` branches that can be consumed
- * independently. Backpressure is enforced by the slowest consumer —
+ * independently. Backpressure is enforced by the slowest consumer –
  * the source only advances once every branch has consumed the current item.
  */
 function tee(source, count) {
     const iterator = source[Symbol.asyncIterator]();
     let current;
-    let consumed = 0;
-    function advance() {
-        if (!current || consumed >= count) {
-            consumed = 0;
+    const consumed = new Array(count).fill(false);
+    const waiting = [];
+    function advance(branch) {
+        // First branch to request a new round fetches from the source.
+        if (!current || consumed.every(Boolean)) {
+            consumed.fill(false);
             current = iterator.next();
         }
-        consumed++;
+        // This branch already consumed the current item – wait for the next round.
+        if (consumed[branch]) {
+            return new Promise(resolve => waiting.push(resolve)).then(() => advance(branch));
+        }
+        consumed[branch] = true;
+        // All branches consumed – wake up any that are waiting for the next round.
+        if (consumed.every(Boolean)) {
+            for (const resolve of waiting.splice(0))
+                resolve();
+        }
         return current;
     }
-    return Array.from({ length: count }, () => ({
+    return Array.from({ length: count }, (_, index) => ({
         [Symbol.asyncIterator]() {
             return {
                 async next() {
-                    return advance();
+                    return advance(index);
                 },
             };
         },

package/dist/plugin/namespaceNormalization.d.ts

@@ -0,0 +1,26 @@
+import type { QuadTransform } from '../stage.js';
+import type { PipelinePlugin } from '../pipeline.js';
+export interface NamespaceNormalizationOptions {
+    /** Namespace URI prefix to match (e.g. `http://schema.org/`). */
+    from: string;
+    /** Namespace URI prefix to replace with (e.g. `https://schema.org/`). */
+    to: string;
+}
+/**
+ * Creates a QuadTransform that rewrites namespace prefixes in `void:class` and
+ * `void:property` quad objects from {@link NamespaceNormalizationOptions.from}
+ * to {@link NamespaceNormalizationOptions.to}.
+ *
+ * `void:vocabulary` quads are left unchanged so consumers can see which
+ * namespace the source dataset actually uses.
+ */
+export declare function namespaceNormalizationTransform(options: NamespaceNormalizationOptions): QuadTransform;
+/**
+ * Pipeline plugin that normalizes namespace prefixes in `void:class` and
+ * `void:property` quad objects.
+ *
+ * `void:vocabulary` quads are left unchanged so consumers can see which
+ * namespace the source dataset actually uses.
+ */
+export declare function namespaceNormalizationPlugin(options: NamespaceNormalizationOptions): PipelinePlugin;
+//# sourceMappingURL=namespaceNormalization.d.ts.map

package/dist/plugin/namespaceNormalization.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"namespaceNormalization.d.ts","sourceRoot":"","sources":["../../src/plugin/namespaceNormalization.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAC,aAAa,EAAC,MAAM,aAAa,CAAC;AAC/C,OAAO,KAAK,EAAC,cAAc,EAAC,MAAM,gBAAgB,CAAC;AASnD,MAAM,WAAW,6BAA6B;IAC5C,iEAAiE;IACjE,IAAI,EAAE,MAAM,CAAC;IACb,yEAAyE;IACzE,EAAE,EAAE,MAAM,CAAC;CACZ;AAED;;;;;;;GAOG;AACH,wBAAgB,+BAA+B,CAC7C,OAAO,EAAE,6BAA6B,GACrC,aAAa,CAEf;AAED;;;;;;GAMG;AACH,wBAAgB,4BAA4B,CAC1C,OAAO,EAAE,6BAA6B,GACrC,cAAc,CAKhB"}

package/dist/plugin/namespaceNormalization.js

@@ -0,0 +1,40 @@
+import { DataFactory } from 'n3';
+const { namedNode, quad } = DataFactory;
+const VOID_CLASS = namedNode('http://rdfs.org/ns/void#class');
+const VOID_PROPERTY = namedNode('http://rdfs.org/ns/void#property');
+/**
+ * Creates a QuadTransform that rewrites namespace prefixes in `void:class` and
+ * `void:property` quad objects from {@link NamespaceNormalizationOptions.from}
+ * to {@link NamespaceNormalizationOptions.to}.
+ *
+ * `void:vocabulary` quads are left unchanged so consumers can see which
+ * namespace the source dataset actually uses.
+ */
+export function namespaceNormalizationTransform(options) {
+    return (quads) => normalizeNamespace(quads, options);
+}
+/**
+ * Pipeline plugin that normalizes namespace prefixes in `void:class` and
+ * `void:property` quad objects.
+ *
+ * `void:vocabulary` quads are left unchanged so consumers can see which
+ * namespace the source dataset actually uses.
+ */
+export function namespaceNormalizationPlugin(options) {
+    return {
+        name: 'namespace-normalization',
+        beforeStageWrite: namespaceNormalizationTransform(options),
+    };
+}
+async function* normalizeNamespace(quads, { from, to }) {
+    for await (const q of quads) {
+        if ((q.predicate.equals(VOID_CLASS) || q.predicate.equals(VOID_PROPERTY)) &&
+            q.object.termType === 'NamedNode' &&
+            q.object.value.startsWith(from)) {
+            yield quad(q.subject, q.predicate, namedNode(to + q.object.value.slice(from.length)), q.graph);
+        }
+        else {
+            yield q;
+        }
+    }
+}

package/dist/plugin/schemaOrgNormalization.d.ts

@@ -1,13 +1,20 @@
 import type { QuadTransform } from '../stage.js';
 import type { PipelinePlugin } from '../pipeline.js';
+export interface SchemaOrgNormalizationOptions {
+    /** When true, normalizes `https://schema.org/` to `http://schema.org/` instead. */
+    reverse?: boolean;
+}
 /** QuadTransform that normalizes `http://schema.org/` to `https://schema.org/` in `void:class` and `void:property` objects. */
 export declare const schemaOrgNormalizationTransform: QuadTransform;
 /**
- * Pipeline plugin that normalizes `http://schema.org/` to `https://schema.org/`
- * in `void:class` and `void:property` quad objects.
+ * Pipeline plugin that normalizes Schema.org namespace prefixes in `void:class`
+ * and `void:property` quad objects.
+ *
+ * By default, rewrites `http://schema.org/` to `https://schema.org/`. Pass
+ * `{ reverse: true }` to normalize in the opposite direction.
  *
  * `void:vocabulary` quads are left unchanged so consumers can see which
  * namespace the source dataset actually uses.
  */
-export declare function schemaOrgNormalizationPlugin(): PipelinePlugin;
+export declare function schemaOrgNormalizationPlugin(options?: SchemaOrgNormalizationOptions): PipelinePlugin;
 //# sourceMappingURL=schemaOrgNormalization.d.ts.map

package/dist/plugin/schemaOrgNormalization.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"schemaOrgNormalization.d.ts","sourceRoot":"","sources":["../../src/plugin/schemaOrgNormalization.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,aAAa,CAAC;AACjD,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAYrD,+HAA+H;AAC/H,eAAO,MAAM,+BAA+B,EAAE,aACnB,CAAC;AAE5B;;;;;;GAMG;AACH,wBAAgB,4BAA4B,IAAI,cAAc,CAK7D"}
+{"version":3,"file":"schemaOrgNormalization.d.ts","sourceRoot":"","sources":["../../src/plugin/schemaOrgNormalization.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAC,aAAa,EAAC,MAAM,aAAa,CAAC;AAC/C,OAAO,KAAK,EAAC,cAAc,EAAC,MAAM,gBAAgB,CAAC;AASnD,MAAM,WAAW,6BAA6B;IAC5C,mFAAmF;IACnF,OAAO,CAAC,EAAE,OAAO,CAAC;CACnB;AAED,+HAA+H;AAC/H,eAAO,MAAM,+BAA+B,EAAE,aAI1C,CAAC;AAEL;;;;;;;;;GASG;AACH,wBAAgB,4BAA4B,CAC1C,OAAO,CAAC,EAAE,6BAA6B,GACtC,cAAc,CAOhB"}

package/dist/plugin/schemaOrgNormalization.js

@@ -1,33 +1,26 @@
-import { DataFactory } from 'n3';
-const { namedNode, quad } = DataFactory;
-const VOID_CLASS = namedNode('http://rdfs.org/ns/void#class');
-const VOID_PROPERTY = namedNode('http://rdfs.org/ns/void#property');
+import { namespaceNormalizationPlugin, namespaceNormalizationTransform, } from './namespaceNormalization.js';
 const HTTP_SCHEMA_ORG = 'http://schema.org/';
 const HTTPS_SCHEMA_ORG = 'https://schema.org/';
 /** QuadTransform that normalizes `http://schema.org/` to `https://schema.org/` in `void:class` and `void:property` objects. */
-export const schemaOrgNormalizationTransform = (quads) => normalizeSchemaOrg(quads);
+export const schemaOrgNormalizationTransform = namespaceNormalizationTransform({
+    from: HTTP_SCHEMA_ORG,
+    to: HTTPS_SCHEMA_ORG,
+});
 /**
- * Pipeline plugin that normalizes `http://schema.org/` to `https://schema.org/`
- * in `void:class` and `void:property` quad objects.
+ * Pipeline plugin that normalizes Schema.org namespace prefixes in `void:class`
+ * and `void:property` quad objects.
+ *
+ * By default, rewrites `http://schema.org/` to `https://schema.org/`. Pass
+ * `{ reverse: true }` to normalize in the opposite direction.
  *
  * `void:vocabulary` quads are left unchanged so consumers can see which
  * namespace the source dataset actually uses.
  */
-export function schemaOrgNormalizationPlugin() {
+export function schemaOrgNormalizationPlugin(options) {
+    const from = options?.reverse ? HTTPS_SCHEMA_ORG : HTTP_SCHEMA_ORG;
+    const to = options?.reverse ? HTTP_SCHEMA_ORG : HTTPS_SCHEMA_ORG;
     return {
+        ...namespaceNormalizationPlugin({ from, to }),
         name: 'schema-org-normalization',
-        beforeStageWrite: schemaOrgNormalizationTransform,
     };
 }
-async function* normalizeSchemaOrg(quads) {
-    for await (const q of quads) {
-        if ((q.predicate.equals(VOID_CLASS) || q.predicate.equals(VOID_PROPERTY)) &&
-            q.object.termType === 'NamedNode' &&
-            q.object.value.startsWith(HTTP_SCHEMA_ORG)) {
-            yield quad(q.subject, q.predicate, namedNode(HTTPS_SCHEMA_ORG + q.object.value.slice(HTTP_SCHEMA_ORG.length)), q.graph);
-        }
-        else {
-            yield q;
-        }
-    }
-}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lde/pipeline",
-  "version": "0.28.6",
+  "version": "0.28.8",
   "repository": {
     "url": "git+https://github.com/ldelements/lde.git",
     "directory": "packages/pipeline"
@@ -29,7 +29,7 @@
     "@lde/sparql-importer": "0.6.0",
     "@lde/sparql-server": "0.4.10",
     "@rdfjs/types": "^2.0.1",
-    "@traqula/generator-sparql-1-1": "^1.0.4",
+    "@traqula/generator-sparql-1-1": "^1.0.6",
     "@traqula/parser-sparql-1-1": "^1.0.4",
     "@traqula/rules-sparql-1-1": "^1.0.4",
     "fetch-sparql-endpoint": "^7.1.0",