Merge pull request #271 from AuScope/dev-sample

Merging Dev sample in master

ckan/src/ckanext-igsn-theme/ckanext/igsn_theme/logic/batch_process.py

@@ -64,6 +64,8 @@ def process_author_emails(sample, authors_df):
 
 def prepare_samples_data(samples_df, authors_df, related_resources_df, funding_df, org_id):
         samples_data = []
+        existing_names = set()
+        errors = []
         for _, row in samples_df.iterrows():
             sample = row.to_dict()
             sample["author"] = process_author_emails(sample, authors_df)
@@ -75,6 +77,10 @@ def prepare_samples_data(samples_df, authors_df, related_resources_df, funding_d
             sample['notes'] = sample['description']
             sample['location_choice'] = 'noLocation'
             sample['parent_sample'] = sample['parent_sample']
+            sample['parent'] = ''
+
+            sample['acquisition_start_date'] = row['acquisition_start_date'].strftime('%Y-%m-%d') if pd.notnull(row['acquisition_start_date']) else None
+            sample['acquisition_end_date'] = row['acquisition_end_date'].strftime('%Y-%m-%d') if pd.notnull(row['acquisition_end_date']) else None
 
             org = toolkit.get_action('organization_show')({}, {'id': org_id})
             sample['owner_org'] = org_id
@@ -98,10 +104,23 @@ def prepare_samples_data(samples_df, authors_df, related_resources_df, funding_d
 
             sample["name"] = generate_sample_name(org_id, sample['sample_type'], sample['sample_number'])
             sample["title"] = generate_sample_title(org_id, sample['sample_type'], sample['sample_number'])
+            # Check for uniqueness
+            if sample["name"] in existing_names:
+                errors.append(f"Duplicate sample name: {sample['name']}")
+            else:
+                existing_names.add(sample["name"])
 
             samples_data.append(sample)
-
-        return samples_data
+            try:
+                package_list = toolkit.get_action('package_list')({}, {})
+                for package in package_list:
+                    package_data = toolkit.get_action('package_show')({}, {'id': package})
+                    existing_name = package_data.get('name')
+                    if existing_name in existing_names:
+                        errors.append(f"Sample name {existing_name} already exists in CKAN")
+            except Exception as e:
+                errors.append(f"Error fetching CKAN data: {str(e)}")
+        return samples_data, errors
 
 def process_related_resources(sample, related_resources_df):
     related_resources_urls = sample.get("related_resources_urls")

ckan/src/ckanext-igsn-theme/ckanext/igsn_theme/templates/batch/create_batch_dataset.html

@@ -70,7 +70,7 @@
       <h1>Upload batch sample metadata</h1>
     </div>
     <div class="col-sm-3 float-right">
-      <a href="/base/files/auscope-sample-template.xlsx" class="btn btn-link" download>
+      <a href="/base/files/auscope-sample-template-v3.xlsx" class="btn btn-link" download>
         <i class="fas fa-upload"></i> Download Template
       </a>
     </div>

ckan/src/ckanext-igsn-theme/ckanext/igsn_theme/templates/home/snippets/about.html

@@ -1,8 +1,24 @@
 {% trans %}
-<p>AuScope focuses on delivering data, services, and tools to support future research in the Australian geoscience research community. As a component of the “Data Lens” of the AuScope Downward-Looking Telescope, the AuScope Discovery Portal harvests metadata from affiliated data catalogues to support more comprehensive access. Over time, it has become apparent that the data repositories, and more specifically sample data repositories, offered by the AuScope partners and universities need to be improved for curating sample data from the AuScope projects. </p>
 
-<p>AuScope is committed to providing a trusted digital repository for its communities (e.g., NCRIS-funded data projects and Australian Geoscience research communities) to curate and publish their sample data following the FAIR Data Guiding Principles. Sample metadata and links to related datasets will be available openly through the repository with appropriate attributions to promote open science. The repository is essential for geoscience research innovation in support of the AuScope 5-Year Investment Plan and Australian Academy of Science Decadal plan for Australian Geoscience: Our Planet, Australia's Future.</p>
+<p> The AuScope Virtual Research Environment (AVRE) is an AuScope program that focuses on delivering data, services, and tools to support the future research of the Australian geoscience research community. AVRE provides a rich ecosystem of Findable, Accessible, Interoperable and Reusable (FAIR) data and tools to a diverse range of Australian research organisations, government geological surveys and the international community. The AVRE program has contributed to the development and spearheaded the adoption of the International Generic Sample Numbers (IGSN) system in Australia in collaboration with the IGSN e.V. Organisation, DataCite, and the Australian Research Data Commons (ARDC).</p>
+<p>
+The AuScope Sample Repository aims to offer a digital repository for the AuScope community to register persistent identifiers for specimen data and publish specimen metadata following the
+<a href="https://www.go-fair.org/fair-principles/" class="custom-link" target="_blank"> FAIR Data Guiding Principles.</a>
+The AuScope communities comprise NCRIS-funded data projects and Australian geoscience research communities. The AuScope Sample Repository is operated as a self-service facility for the storage, dissemination, and publication of metadata from AuScope-funded projects and instruments.
+</p>
+{% endtrans %}
 
-<p>This work is supported by AuScope and funded by the Australian Government through the National Collaborative Research Infrastructure Strategy, NCRIS.</p>
+<style>
+
+  .custom-link {
+    color: var(--color-aus-royal-blue);
+    text-decoration: none;
+    font-weight: bold;
+  }
 
-{% endtrans %}
+  .custom-link:hover {
+    text-decoration: underline;
+    color: var(--color-aus-royal-blue);
+    font-weight: bold;
+  }
+</style>

ckan/src/ckanext-igsn-theme/ckanext/igsn_theme/templates/home/snippets/instructions.html

@@ -17,7 +17,7 @@ <h1 class="page-heading">{{ _("Quick Start") }}</h1>
             <li>
                 <span class="badge">Start Batch Upload</span>
                 (register multiple samples by uploading a 
-                <a href="/base/files/auscope-sample-template.xlsx" class="custom-link">spreadsheet</a>
+                <a href="/base/files/auscope-sample-template-v3.xlsx" class="custom-link">spreadsheet</a>
                 )
             </li>          
           </ul>
@@ -34,7 +34,7 @@ <h1 class="page-heading">{{ _("Quick Start") }}</h1>
             <li>
                 <span class="badge">Start Batch Upload</span>
                 (register multiple samples by uploading a 
-                <a href="/base/files/auscope-sample-template.xlsx" class="custom-link">spreadsheet</a>
+                <a href="/base/files/auscope-sample-template-v3.xlsx" class="custom-link">spreadsheet</a>
                 )
             </li>   
           </ul>

ckan/src/ckanext-igsn-theme/ckanext/igsn_theme/views.py

@@ -85,16 +85,18 @@ def process_excel(self, uploaded_file, org_id):
             all_errors.extend(validate_related_resources(related_resources_df))
             all_errors.extend(validate_parent_samples(samples_df))
 
+
+
+            samples_data, errors = prepare_samples_data(samples_df, authors_df, related_resources_df, funding_df, org_id)
+            all_errors.extend(errors)
+
             if all_errors:
                 error_list = "\n".join(f"Error {i+1}. {error}. " for i, error in enumerate(all_errors))
                 # format the error list to be displayed in human readable format
                 formatted_errors = f"<pre style='white-space: pre-wrap;'>{error_list}</pre>"
                 raise ValueError(f"""The following errors were found:
                     {formatted_errors}""")
 
-            samples_data = prepare_samples_data(samples_df, authors_df, related_resources_df, funding_df, org_id)
-
-
             return_value = {
                 "samples": samples_data,
                 "authors": authors_df.to_dict("records"),