NickAkhmetov/CAT-881 deduplicate errored processed datasets' urls (#3558

)

CHANGELOG-cat-881.md

@@ -0,0 +1 @@
+- Append HuBMAP ID to errored datasets' URL anchors to avoid anchor duplication on dataset pages with multiple failed processing attempts.

context/app/static/js/pages/Dataset/utils.spec.ts

@@ -0,0 +1,42 @@
+import { datasetSectionId } from './utils';
+
+const prefix = 'prefix';
+
+describe('datasetSectionId', () => {
+  it('should format the dataset section id correctly', () => {
+    const dataset = {
+      pipeline: 'pipeline',
+      hubmap_id: 'hubmap_id',
+      status: 'status',
+    };
+    expect(datasetSectionId(dataset, prefix)).toBe('prefix-pipeline-status');
+  });
+  it('Should include the hubmap id if the pipeline is missing', () => {
+    const dataset = {
+      hubmap_id: 'hubmap_id',
+      status: 'status',
+    };
+    expect(datasetSectionId(dataset, prefix)).toBe('prefix-hubmap_id-status');
+  });
+  it('should include the pipeline and hubmap_id if the pipeline is errored', () => {
+    const dataset = {
+      pipeline: 'pipeline',
+      hubmap_id: 'hubmap_id',
+      status: 'error',
+    };
+    expect(datasetSectionId(dataset, prefix)).toBe('prefix-pipeline-error-hubmap_id');
+  });
+  it('should generate unique ids for different errored datasets', () => {
+    const dataset1 = {
+      pipeline: 'pipeline',
+      hubmap_id: 'hubmap_id',
+      status: 'error',
+    };
+    const dataset2 = {
+      pipeline: 'pipeline',
+      hubmap_id: 'hubmap_id_2',
+      status: 'error',
+    };
+    expect(datasetSectionId(dataset1, prefix)).not.toBe(datasetSectionId(dataset2, prefix));
+  });
+});

context/app/static/js/pages/Dataset/utils.ts

@@ -1,11 +1,16 @@
 import { ProcessedDatasetInfo } from './hooks';
 
+const potentialDuplicateStates = ['error'];
+
 export function datasetSectionId(
-  dataset: Pick<ProcessedDatasetInfo, 'pipeline' | 'hubmap_id' | 'status'>,
+  dataset: Pick<ProcessedDatasetInfo, 'hubmap_id' | 'status'> & { pipeline?: string },
   prefix = '',
 ) {
   const { pipeline, hubmap_id, status } = dataset;
   const formattedDatasetIdentifier = (pipeline ?? hubmap_id).replace(/\s/g, '');
   const formattedStatus = status.replace(/\s/g, '');
-  return `${prefix}-${encodeURIComponent(formattedDatasetIdentifier)}-${encodeURIComponent(formattedStatus)}`.toLowerCase();
+  const deduplicatedFormattedStatus = potentialDuplicateStates.includes(formattedStatus.toLowerCase())
+    ? `${formattedStatus}-${hubmap_id}`
+    : formattedStatus;
+  return `${prefix}-${encodeURIComponent(formattedDatasetIdentifier)}-${encodeURIComponent(deduplicatedFormattedStatus)}`.toLowerCase();
 }