feat: Catalog component API and docs improvements

packages/components/src/components/Catalog.tsx

@@ -7,7 +7,12 @@ export function Catalog({
   datasets,
   facets,
 }: {
-  datasets: any[];
+  datasets: {
+    _id: string | number;
+    metadata: { title: string; [k: string]: string | number };
+    url_path: string;
+    [k: string]: any;
+  }[];
   facets: string[];
 }) {
   const [indexFilter, setIndexFilter] = useState('');
@@ -56,7 +61,7 @@ export function Catalog({
     //Then check if the selectedValue for the given facet is included in the dataset metadata
     .filter((dataset) => {
       //Avoids a server rendering breakage
-      if (!watch() || Object.keys(watch()).length === 0) return true
+      if (!watch() || Object.keys(watch()).length === 0) return true;
       //This will filter only the key pairs of the metadata values that were selected as facets
       const datasetFacets = Object.entries(dataset.metadata).filter((entry) =>
         facets.includes(entry[0])
@@ -86,9 +91,7 @@ export function Catalog({
           className="p-2 ml-1 text-sm shadow border border-block"
           {...register(elem[0] + '.selectedValue')}
         >
-          <option value="">
+          <option value="">Filter by {elem[0]}</option>
-            Filter by {elem[0]}
-          </option>
           {(elem[1] as { possibleValues: string[] }).possibleValues.map(
             (val) => (
               <option
@@ -102,10 +105,10 @@ export function Catalog({
           )}
         </select>
       ))}
-      <ul className='mb-5 pl-6 mt-5 list-disc'>
+      <ul className="mb-5 pl-6 mt-5 list-disc">
         {filteredDatasets.map((dataset) => (
-          <li className='py-2' key={dataset._id}>
+          <li className="py-2" key={dataset._id}>
-            <a className='font-medium underline' href={dataset.url_path}>
+            <a className="font-medium underline" href={dataset.url_path}>
               {dataset.metadata.title
                 ? dataset.metadata.title
                 : dataset.url_path}
@@ -116,4 +119,3 @@ export function Catalog({
     </>
   );
 }
-

packages/components/stories/Catalog.stories.ts

@@ -10,11 +10,14 @@ const meta: Meta = {
   argTypes: {
     datasets: {
       description:
-        'Lists of datasets to be displayed in the list, will usually be automatically available',
+        "Array of items to be displayed on the searchable list. Must have the following properties: \n\n \
+`_id`: item's unique id \n\n \
+`url_path`: href of the item \n\n \
+`metadata`: object with a `title` property, that will be displayed as the title of the item, together with any other custom fields that might or not be faceted.",
     },
     facets: {
       description:
-        'List of frontmatter fields that should be used as filters, needs to match exactly with the field name',
+        "Array of strings, which are name of properties in the datasets' `metadata`, which are going to be faceted.",
     },
   },
 };
@@ -31,99 +34,35 @@ export const WithoutFacets: Story = {
       {
         _id: '07026b22d49916754df1dc8ffb9ccd1c31878aae',
         url_path: 'dataset-4',
-        file_path: 'content/dataset-4/index.md',
         metadata: {
           title: 'Detecting Abusive Albanian',
-          'link-to-publication': 'https://arxiv.org/abs/2107.13592',
-          'link-to-data': 'https://doi.org/10.6084/m9.figshare.19333298.v1',
-          'task-description':
-            'Hierarchical (offensive/not; untargeted/targeted; person/group/other)',
-          'details-of-task':
-            'Detect and categorise abusive language in social media data',
-          'size-of-dataset': 11874,
-          'percentage-abusive': 13.2,
-          language: 'Albanian',
-          'level-of-annotation': ['Posts'],
-          platform: ['Instagram', 'Youtube'],
-          medium: ['Text'],
-          reference:
-            'Nurce, E., Keci, J., Derczynski, L., 2021. Detecting Abusive Albanian. arXiv:2107.13592',
         },
       },
       {
         _id: '42c86cf3c4fbbab11d91c2a7d6dcb8f750bc4e19',
         url_path: 'dataset-1',
-        file_path: 'content/dataset-1/index.md',
         metadata: {
           title: 'AbuseEval v1.0',
-          'link-to-publication':
-            'http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.760.pdf',
-          'link-to-data': 'https://github.com/tommasoc80/AbuseEval',
-          'task-description':
-            'Explicitness annotation of offensive and abusive content',
-          'details-of-task':
-            'Enriched versions of the OffensEval/OLID dataset with the distinction of explicit/implicit offensive messages and the new dimension for abusive messages. Labels for offensive language: EXPLICIT, IMPLICT, NOT; Labels for abusive language: EXPLICIT, IMPLICT, NOTABU',
-          'size-of-dataset': 14100,
-          'percentage-abusive': 20.75,
-          language: 'English',
-          'level-of-annotation': ['Tweets'],
-          platform: ['Twitter'],
-          medium: ['Text'],
-          reference:
-            'Caselli, T., Basile, V., Jelena, M., Inga, K., and Michael, G. 2020. "I feel offended, don’t be abusive! implicit/explicit messages in offensive and abusive language". The 12th Language Resources and Evaluation Conference (pp. 6193-6202). European Language Resources Association.',
         },
       },
       {
         _id: '80001dd32a752421fdcc64e91fbd237dc31d6bb3',
         url_path: 'dataset-2',
-        file_path: 'content/dataset-2/index.md',
         metadata: {
           title:
             'Abusive Language Detection on Arabic Social Media (Al Jazeera)',
-          'link-to-publication': 'https://www.aclweb.org/anthology/W17-3008',
-          'link-to-data':
-            'http://alt.qcri.org/~hmubarak/offensive/AJCommentsClassification-CF.xlsx',
-          'task-description':
-            'Ternary (Obscene, Offensive but not obscene, Clean)',
-          'details-of-task': 'Incivility',
-          'size-of-dataset': 32000,
-          'percentage-abusive': 0.81,
-          language: 'Arabic',
-          'level-of-annotation': ['Posts'],
-          platform: ['AlJazeera'],
-          medium: ['Text'],
-          reference:
-            'Mubarak, H., Darwish, K. and Magdy, W., 2017. Abusive Language Detection on Arabic Social Media. In: Proceedings of the First Workshop on Abusive Language Online. Vancouver, Canada: Association for Computational Linguistics, pp.52-56.',
         },
       },
       {
         _id: '96649d05d8193f4333b10015af76c6562971bd8c',
         url_path: 'dataset-3',
-        file_path: 'content/dataset-3/index.md',
         metadata: {
           title: 'CoRAL: a Context-aware Croatian Abusive Language Dataset',
-          'link-to-publication':
-            'https://aclanthology.org/2022.findings-aacl.21/',
-          'link-to-data':
-            'https://github.com/shekharRavi/CoRAL-dataset-Findings-of-the-ACL-AACL-IJCNLP-2022',
-          'task-description':
-            'Multi-class based on context dependency categories (CDC)',
-          'details-of-task': 'Detectioning CDC from abusive comments',
-          'size-of-dataset': 2240,
-          'percentage-abusive': 100,
-          language: 'Croatian',
-          'level-of-annotation': ['Posts'],
-          platform: ['Posts'],
-          medium: ['Newspaper Comments'],
-          reference:
-            'Ravi Shekhar, Mladen Karan and Matthew Purver (2022). CoRAL: a Context-aware Croatian Abusive Language Dataset. Findings of the ACL: AACL-IJCNLP.',
         },
       },
     ],
   },
 };
-;
-
 export const WithFacets: Story = {
   name: 'Catalog with facets',
   args: {
@@ -131,7 +70,6 @@ export const WithFacets: Story = {
       {
         _id: '07026b22d49916754df1dc8ffb9ccd1c31878aae',
         url_path: 'dataset-4',
-        file_path: 'content/dataset-4/index.md',
         metadata: {
           title: 'Detecting Abusive Albanian',
           'link-to-publication': 'https://arxiv.org/abs/2107.13592',
@@ -220,7 +158,6 @@ export const WithFacets: Story = {
         },
       },
     ],
-    facets: ['language', 'platform']
+    facets: ['language', 'platform'],
   },
 };
-;