@lde/pipeline-shacl-sampler 0.3.2 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +16 -13
  2. package/dist/sampleStages.d.ts +1 -1
  3. package/dist/sampleStages.js +1 -1
  4. package/package.json +2 -2
package/README.md CHANGED
@@ -19,12 +19,15 @@ validate without false-positive ‘missing nested node’ violations.
19
19
  ## Usage
20
20
 
21
21
  ```typescript
22
- import { Pipeline } from '@lde/pipeline';
22
+ import { Pipeline, FileWriter } from '@lde/pipeline';
23
23
  import { shaclSampleStages } from '@lde/pipeline-shacl-sampler';
24
24
  import { ShaclValidator } from '@lde/pipeline-shacl-validator';
25
25
 
26
26
  const shapesFile = 'https://docs.nde.nl/schema-profile/shacl.ttl';
27
- const validator = new ShaclValidator({ shapesFile, reportDir: './validation' });
27
+ const validator = new ShaclValidator({
28
+ shapesFile,
29
+ reportWriters: [new FileWriter({ outputDir: './validation', format: 'turtle' })],
30
+ });
28
31
 
29
32
  const stages = await shaclSampleStages({
30
33
  shapesFile,
@@ -37,16 +40,16 @@ await new Pipeline({ /* … */, stages }).run();
37
40
 
38
41
  ## Options
39
42
 
40
- | Option | Default | Description |
41
- | ----------------- | ----------------- | ---------------------------------------------------------------------------------------------------------------------- |
42
- | `shapesFile` | — | URL or local path to the SHACL shapes file. Any format `rdf-dereference` accepts. |
43
- | `samplesPerClass` | `50` | Number of top-level resources to sample per `sh:targetClass`. |
44
- | `timeout` | `60000` | SPARQL query timeout in milliseconds. |
45
- | `batchSize` | `samplesPerClass` | Maximum sampled subjects per executor call. Lower values spread work across multiple parallel queries. |
46
- | `maxConcurrency` | `10` | Maximum concurrent in-flight executor batches per stage. |
47
- | `validator` | — | Optional [`Validator`](../pipeline/src/validator.ts) attached to every generated stage (typically a `ShaclValidator`). |
48
- | `onInvalid` | `'write'` | Behaviour when a sampled batch fails validation: `'write'` \| `'skip'` \| `'halt'`. Only used when `validator` is set. |
49
- | `namespaceAliases`| `[]` | Namespaces to treat as equivalent when matching `sh:targetClass` and when handing quads to the validator. See [Namespace aliases](#namespace-aliases). |
43
+ | Option | Default | Description |
44
+ | ------------------ | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
45
+ | `shapesFile` | — | URL or local path to the SHACL shapes file. Any format `rdf-dereference` accepts. |
46
+ | `samplesPerClass` | `50` | Number of top-level resources to sample per `sh:targetClass`. |
47
+ | `timeout` | `60000` | SPARQL query timeout in milliseconds. |
48
+ | `batchSize` | `samplesPerClass` | Maximum sampled subjects per executor call. Lower values spread work across multiple parallel queries. |
49
+ | `maxConcurrency` | `10` | Maximum concurrent in-flight executor batches per stage. |
50
+ | `validator` | — | Optional [`Validator`](../pipeline/src/validator.ts) attached to every generated stage (typically a `ShaclValidator`). |
51
+ | `onInvalid` | `'write'` | Behaviour when a sampled batch fails validation: `'write'` \| `'skip'` \| `'halt'`. Only used when `validator` is set. |
52
+ | `namespaceAliases` | `[]` | Namespaces to treat as equivalent when matching `sh:targetClass` and when handing quads to the validator. See [Namespace aliases](#namespace-aliases). |
50
53
 
51
54
  ## Namespace aliases
52
55
 
@@ -60,7 +63,7 @@ report vacuously-conformant runs against datasets that mix the two.
60
63
  `namespaceAliases` closes the gap. For every declared pair the sampler:
61
64
 
62
65
  - broadens its subject-selection SELECT to `?s a ?type . FILTER(?type IN
63
- (<canonical/X>, <alias/X>))`, so instances typed under either
66
+ (<canonical/X>, <alias/X>))`, so instances typed under either
64
67
  namespace are picked up;
65
68
  - decorates the configured `validator` so any alias-namespace IRI in
66
69
  the sampled quads is rewritten to the canonical form before the SHACL
package/dist/sampleStages.d.ts CHANGED
@@ -86,7 +86,7 @@ export interface ShaclSampleStagesOptions {
86
86
  * Pass a {@link Validator} to attach it to every generated stage:
87
87
  *
88
88
  * ```ts
89
- * const validator = new ShaclValidator({ shapesFile, reportDir });
89
+ * const validator = new ShaclValidator({ shapesFile, reportWriters: [...] });
90
90
  * const stages = await shaclSampleStages({ shapesFile, validator });
91
91
  * ```
92
92
  */
package/dist/sampleStages.js CHANGED
@@ -14,7 +14,7 @@ const { namedNode, quad } = DataFactory;
14
14
  * Pass a {@link Validator} to attach it to every generated stage:
15
15
  *
16
16
  * ```ts
17
- * const validator = new ShaclValidator({ shapesFile, reportDir });
17
+ * const validator = new ShaclValidator({ shapesFile, reportWriters: [...] });
18
18
  * const stages = await shaclSampleStages({ shapesFile, validator });
19
19
  * ```
20
20
  */
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@lde/pipeline-shacl-sampler",
3
- "version": "0.3.2",
3
+ "version": "0.4.0",
4
4
  "description": "Per-class sampling stages for @lde/pipeline, derived from SHACL shapes",
5
5
  "repository": {
6
6
  "url": "git+https://github.com/ldelements/lde.git",
@@ -32,6 +32,6 @@
32
32
  },
33
33
  "peerDependencies": {
34
34
  "@lde/dataset": "0.7.4",
35
- "@lde/pipeline": "0.29.2"
35
+ "@lde/pipeline": "0.30.0"
36
36
  }
37
37
  }