hot-fix: Add ORCID validation and improve dataset editing UX

### Major Features
- Add comprehensive ORCID validation with checksum verification
- Implement unsaved changes detection and auto-save functionality
- Enhanced form component reactivity and state management

### ORCID Implementation
- Create custom VineJS ORCID validation rule with MOD-11-2 algorithm
- Add ORCID fields to Person model and TablePersons component
- Update dataset validators to include ORCID validation
- Add descriptive placeholder text for ORCID input fields

### UI/UX Improvements
- Add UnsavedChangesWarning component with detailed change tracking
- Improve FormCheckRadio and FormCheckRadioGroup reactivity
- Enhanced BaseButton with proper disabled state handling
- Better error handling and user feedback in file validation

### Data Management
- Implement sophisticated change detection for all dataset fields
- Add proper handling of array ordering for authors/contributors
- Improve license selection with better state management
- Enhanced subject/keyword processing with duplicate detection

### Technical Improvements
- Optimize search indexing with conditional updates based on modification dates
- Update person model column mapping for ORCID
- Improve validation error messages and user guidance
- Better handling of file uploads and deletion tracking

### Dependencies
- Update various npm packages (AWS SDK, Babel, Vite, etc.)
- Add baseline-browser-mapping for better browser compatibility

### Bug Fixes
- Fix form reactivity issues with checkbox/radio groups
- Improve error handling in file validation rules
- Better handling of edge cases in change detection

commands/index_datasets.ts

@@ -12,10 +12,8 @@ import { getDomain } from '#app/utils/utility-functions';
 import { BaseCommand, flags } from '@adonisjs/core/ace';
 import { CommandOptions } from '@adonisjs/core/types/ace';
 import env from '#start/env';
-// import db from '@adonisjs/lucid/services/db';
-// import { default as Dataset } from '#models/dataset';
 import logger from '@adonisjs/core/services/logger';
-
+import { DateTime } from 'luxon';
 
 const opensearchNode = env.get('OPENSEARCH_HOST', 'localhost');
 const client = new Client({ node: `${opensearchNode}` }); // replace with your OpenSearch endpoint
@@ -30,11 +28,10 @@ export default class IndexDatasets extends BaseCommand {
     public publish_id: number;
 
     public static options: CommandOptions = {
-        startApp: true,       
-        staysAlive: false,
+        startApp: true, // Ensures the IoC container is ready to use
+        staysAlive: false, // Command exits after running
     };
 
-
     async run() {
         logger.debug('Hello world!');
         // const { default: Dataset } = await import('#models/dataset');
@@ -44,10 +41,12 @@ export default class IndexDatasets extends BaseCommand {
         const index_name = 'tethys-records';
 
         for (var dataset of datasets) {
-            // Logger.info(`File publish_id ${dataset.publish_id}`);
-            // const jsonString = await this.getJsonString(dataset, proc);
-            // console.log(jsonString);
-            await this.indexDocument(dataset, index_name, proc);
+            const shouldUpdate = await this.shouldUpdateDataset(dataset, index_name);
+            if (shouldUpdate) {
+                await this.indexDocument(dataset, index_name, proc);
+            } else {
+                logger.info(`Dataset with publish_id ${dataset.publish_id} is up to date, skipping indexing`);
+            }
         }
     }
 
@@ -65,6 +64,46 @@ export default class IndexDatasets extends BaseCommand {
         return await query.exec();
     }
 
+    private async shouldUpdateDataset(dataset: Dataset, index_name: string): Promise<boolean> {
+        try {
+            // Check if publish_id exists before proceeding
+            if (!dataset.publish_id) {
+                // Return true to update since document doesn't exist in OpenSearch yet
+                return true;
+            }
+            // Get the existing document from OpenSearch
+            const response = await client.get({
+                index: index_name,
+                id: dataset.publish_id?.toString(),
+            });
+
+            const existingDoc = response.body._source;
+
+            // Compare server_date_modified
+            if (existingDoc && existingDoc.server_date_modified) {
+                // Convert Unix timestamp (seconds) to milliseconds for DateTime.fromMillis()
+                const existingModified = DateTime.fromMillis(Number(existingDoc.server_date_modified) * 1000);
+                const currentModified = dataset.server_date_modified;
+
+                // Only update if the dataset has been modified more recently
+                if (currentModified <= existingModified) {
+                    return false;
+                }
+            }
+
+            return true;
+        } catch (error) {
+            // If document doesn't exist or other error, we should index it
+            if (error.statusCode === 404) {
+                logger.info(`Dataset with publish_id ${dataset.publish_id} not found in index, will create new document`);
+                return true;
+            }
+
+            logger.warn(`Error checking existing document for publish_id ${dataset.publish_id}: ${error.message}`);
+            return true; // Index anyway if we can't determine the status
+        }
+    }
+
     private async indexDocument(dataset: Dataset, index_name: string, proc: Buffer): Promise<void> {
         try {
             const doc = await this.getJsonString(dataset, proc);
@@ -78,7 +117,8 @@ export default class IndexDatasets extends BaseCommand {
             });
             logger.info(`dataset with publish_id ${dataset.publish_id} successfully indexed`);
         } catch (error) {
-            logger.error(`An error occurred while indexing dataset with publish_id ${dataset.publish_id}.`);
+            logger.error(`An error occurred while indexing dataset with publish_id ${dataset.publish_id}.
+                Error: ${error.message}`);
         }
     }