Y25-286 - Consolidate accession sample tags

.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config --no-exclude-limit`
-# on 2025-11-26 13:13:53 UTC using RuboCop version 1.81.7.
+# on 2025-11-28 17:57:54 UTC using RuboCop version 1.81.7.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
@@ -299,14 +299,15 @@ Lint/UselessOr:
     - 'app/models/qcable/statemachine.rb'
     - 'app/models/ui_helper/summary.rb'
 
-# Offense count: 6
+# Offense count: 7
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
     - 'app/controllers/api/v2/transfers_controller.rb'
     - 'app/jobs/export_pool_xp_to_traction_job.rb'
     - 'app/models/accession_service/base_service.rb'
     - 'app/sample_manifest_excel/sample_manifest_excel/manifest_type_list.rb'
+    - 'lib/insdc/import_countries.rb'
 
 # Offense count: 1
 # Configuration parameters: CountComments, Max, CountAsOne, AllowedMethods, AllowedPatterns, inherit_mode.
@@ -329,7 +330,7 @@ Metrics/CyclomaticComplexity:
     - 'app/models/accession_service/base_service.rb'
     - 'lib/limber/helper.rb'
 
-# Offense count: 13
+# Offense count: 14
 # Configuration parameters: CountComments, Max, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Exclude:
@@ -340,6 +341,7 @@ Metrics/MethodLength:
     - 'app/models/plate/quad_creator.rb'
     - 'app/uat_actions/uat_actions/tube_submission.rb'
     - 'app/validators/novaseqx_pe_validator.rb'
+    - 'lib/insdc/import_countries.rb'
     - 'lib/record_loader/application_record_loader.rb'
     - 'test/unit/import_fluidigm_data_test.rb'
 

app/models/insdc/country.rb

@@ -48,6 +48,10 @@ def self.options
       sorted_for_select.pluck(:name)
     end
 
+    def valid!
+      update!(validation_state: :valid)
+    end
+
     def invalid!
       update!(validation_state: :invalid)
     end

config/accession/tags.yml

@@ -1,3 +1,20 @@
+# Tags configuration for Accession::TagList
+#
+# Tag/field requirements, naming, and validation can be found in the checklists listed below:
+#
+# - ENA: https://www.ebi.ac.uk/ena/browser/view/ERC000011
+# - EGA: https://www.ebi.ac.uk/ena/browser/view/ERC000026
+# - ArrayExpress: From September 2022, the interface to ArrayExpress was retired:
+#                 https://www.ebi.ac.uk/about/news/updates-from-data-resources/arrayexpress-retired/
+#                 However, it appears that as of February 2017, ENA was submitting samples to ArrayExpress on our behalf.
+#                 See this sample for an example:
+#                 1. https://sequencescape.psd.sanger.ac.uk/samples/2934454
+#                 2. https://www.ebi.ac.uk/ena/browser/view/ERS1545406
+#                 3. https://www.ebi.ac.uk/biosamples/samples/SAMEA80468668
+#                 How samples are being submitted to ArrayExpress/BioSample now is currently unknown.
+#
+# Local copies are also stored in `data/sample_checklists/` for reference purposes as they do change occasionally.
+
 sample_taxon_id:
   services:
     - :ENA
@@ -26,6 +43,13 @@ date_of_sample_collection:
   groups:
     - :sample_attributes
   ebi_name: :collection_date
+sample_description:
+  services:
+    - :ENA
+    - :EGA
+  groups:
+    - :sample_attributes
+  ebi_name: :sample description
 donor_id:
   services:
     - :EGA
@@ -46,6 +70,13 @@ phenotype:
   groups:
     - :sample_attributes
     - :array_express
+sample_strain_att:
+  services:
+    - :ENA
+    - :EGA
+  groups:
+    - :sample_attributes
+  ebi_name: :strain
 strain_or_line:
   groups:
     - :array_express

config/locales/metadata/en.yml

@@ -174,12 +174,14 @@ en:
 
         gender:
           label: Gender
-          edit_info: "Array Express"
+          help: "EGA is limited to Male, Female, or Unknown."
+          edit_info: "EGA, Array Express"
 
         country_of_origin:
           label: Country of origin
           help: The geographic origin of the sample, as defined by the <a href="http://insdc.org/country.html">INSDC list of countries and seas</a>. May also be 'not provided', 'not applicable', 'not collected' or 'restricted access'. Please see <a href="https://ena-docs.readthedocs.io/en/latest/submit/samples/missing-values.html">the missing value documentation</a> before providing one of these values.
           accessioning_tag: geographic location (country and/or sea)
+          edit_info: "ENA requirement"
 
         geographical_region:
           label: Geographical region
@@ -252,6 +254,7 @@ en:
           label: Date of sample collection
           help: Dates should be in the format YYYY-MM-DDTHH:MM:SS (eg. '2020-01-25T12:59:59') with each additional level of precision being optional. May also be 'not provided', 'not collected' or 'restricted access'. Please see <a href="https://ena-docs.readthedocs.io/en/latest/submit/samples/missing-values.html">the missing value documentation</a> before providing one of these values.
           accessioning_tag: collection_date
+          edit_info: "ENA requirement"
 
         date_of_sample_extraction:
           label: Date of sample extraction
@@ -280,7 +283,7 @@ en:
         donor_id:
           label: Donor Id
           ena_label: subject_id
-          edit_info: "EGA (As subject id)"
+          edit_info: "EGA recommended (As subject id)"
 
         subject_id:
           label: subject_id
@@ -291,7 +294,7 @@ en:
           edit_info: "Array Express"
         phenotype:
           label: Phenotype
-          edit_info: "Array Express"
+          edit_info: "EGA requirement, Array Express"
         strain_or_line:
           label: Strain or Line
           edit_info: "Array Express"