Enforce strict creator_{type}_{id} pattern using filename only

example_traject_config_eac_cpf.rb

@@ -22,6 +22,9 @@
 # EAC-CPF namespace - used consistently throughout this config
 EAC_NS = { 'eac' => 'urn:isbn:1-931666-33-4' }
 
+# Pattern matching arcflow's creator file naming: creator_{entity_type}_{id}
+CREATOR_ID_PATTERN = /^creator_(corporate_entities|people|families)_\d+$/
+
 settings do
   provide "solr.url", ENV['SOLR_URL'] || "http://localhost:8983/solr/blacklight-core"
   provide "solr_writer.commit_on_close", "true"
@@ -38,85 +41,21 @@
   context.clipboard[:is_creator] = true
 end
 
-# Core identity field
-# CRITICAL: The 'id' field is required by Solr's schema (uniqueKey)
-# Must ensure this field is never empty or indexing will fail
-#
-# IMPORTANT: Real EAC-CPF from ArchivesSpace has empty <control/> element!
-# Cannot rely on recordId being present. Must extract from filename or generate.
+# Solr uniqueKey - extract ID from filename using arcflow's creator_{entity_type}_{id} pattern
 to_field 'id' do |record, accumulator, context|
-  # Try 1: Extract from control/recordId (if present)
-  record_id = record.xpath('//eac:control/eac:recordId', EAC_NS).first
-  record_id ||= record.xpath('//control/recordId').first
-
-  if record_id && !record_id.text.strip.empty?
-    accumulator << record_id.text.strip
-  else
-    # Try 2: Extract from source filename (most reliable for ArchivesSpace exports)
-    # Filename format: creator_corporate_entities_584.xml or similar
-    source_file = context.source_record_id || context.input_name
-    if source_file
-      # Remove .xml extension and any path
-      id_from_filename = File.basename(source_file, '.xml')
-      # Check if it looks valid (starts with creator_ or agent_)
-      if id_from_filename =~ /^(creator_|agent_)/
-        accumulator << id_from_filename
-        context.logger.info("Using filename-based ID: #{id_from_filename}")
-      else
-        # Try 3: Generate from entity type and name
-        entity_type = record.xpath('//eac:cpfDescription/eac:identity/eac:entityType', EAC_NS).first&.text&.strip
-        name_entry = record.xpath('//eac:cpfDescription/eac:identity/eac:nameEntry/eac:part', EAC_NS).first&.text&.strip
-
-        if entity_type && name_entry
-          # Create stable ID from type and name
-          type_short = case entity_type
-                      when 'corporateBody' then 'corporate'
-                      when 'person' then 'person'
-                      when 'family' then 'family'
-                      else 'entity'
-                      end
-          name_id = name_entry.gsub(/[^a-z0-9]/i, '_').downcase[0..50] # Limit length
-          generated_id = "creator_#{type_short}_#{name_id}"
-          accumulator << generated_id
-          context.logger.warn("Generated ID from name: #{generated_id}")
-        else
-          # No valid ID available - skip indexing this record
-          # If we reach here, something has gone wrong with the data pipeline:
-          # - No recordId in XML
-          # - Filename doesn't match expected pattern
-          # - No entity type or name in XML to generate from
-          # Skipping ensures we don't create non-deterministic IDs that break idempotent indexing
-          context.logger.error("Cannot generate valid ID for record - skipping indexing. Source: #{source_file}")
-          context.skip!("Missing required ID data")
-        end
-      end
+  source_file = context.source_record_id || context.input_name
+  if source_file
+    id_from_filename = File.basename(source_file, '.xml')
+    if id_from_filename =~ CREATOR_ID_PATTERN
+      accumulator << id_from_filename
+      context.logger.info("Using filename-based ID: #{id_from_filename}")
     else
-      # No filename available, generate from name
-      entity_type = record.xpath('//eac:cpfDescription/eac:identity/eac:entityType', EAC_NS).first&.text&.strip
-      name_entry = record.xpath('//eac:cpfDescription/eac:identity/eac:nameEntry/eac:part', EAC_NS).first&.text&.strip
-
-      if entity_type && name_entry
-        type_short = case entity_type
-                    when 'corporateBody' then 'corporate'
-                    when 'person' then 'person'
-                    when 'family' then 'family'
-                    else 'entity'
-                    end
-        name_id = name_entry.gsub(/[^a-z0-9]/i, '_').downcase[0..50]
-        generated_id = "creator_#{type_short}_#{name_id}"
-        accumulator << generated_id
-        context.logger.warn("Generated ID from name: #{generated_id}")
-      else
-        # No valid ID available - skip indexing this record
-        # If we reach here, something has gone wrong with the data pipeline:
-        # - No recordId in XML
-        # - No filename available
-        # - No entity type or name in XML to generate from
-        # Skipping ensures we don't create non-deterministic IDs that break idempotent indexing
-        context.logger.error("Cannot generate valid ID for record - skipping indexing. No filename or entity data available.")
-        context.skip!("Missing required ID data")
-      end
+      context.logger.error("Filename doesn't match expected pattern 'creator_{type}_{id}': #{id_from_filename}")
+      context.skip!("Invalid ID format in filename")
     end
+  else
+    context.logger.error("No source filename available for record")
+    context.skip!("Missing source filename")
   end
 end