pennmarc 1.0.12 → 1.0.15.pre

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 97610e7a00a2d206d84d5865ce9ebf14b5aa43e8081d9c4f559d198cc7adde23
-  data.tar.gz: fcee05f6a1999b674cb699605ee1e16b04fdda87e6bb7e65c3cb54958ef19ba5
+  metadata.gz: cd846248b3c6fcde1cfd8a74312d84f46ce28f534effaff22ec112a5456afd2f
+  data.tar.gz: 7e5789d9ef2594767e438a5b1fd2978b1508afad975785059b3520d795fda15b
 SHA512:
-  metadata.gz: '0099dbb3f521e56f8ba94527e13085058191acfdaa3625f30f050da3bb96d8ae224eb9c6e9fb54620ea6d4640800bc38bd71602a59d66871eedd26c7f6287b4e'
-  data.tar.gz: 44cfade6b9c3ab3e0591553fbdf5c09f8be3467ccf71b0f003f7f0ff9dc8b08b1093d783b84c5f71ba3c98607a2d97f1e1ef62653cbe3af5361895d3cf964c1e
+  metadata.gz: 82a79402e68c4b48f3d38fa165042472aab3a8d811797145811af8a873d177ceb9020a2e71c9853f5c792a37d0533d7a87c7ec94506507c817e3dc09db345dcf
+  data.tar.gz: 87196088380e9b7f6750511434edcc49467ca9ee47e9577cb3f42ce75e595a2f7cb62605ede37d1a4b17b59876dec437a0beee131ee97eb19f1c411751c849cc

data/.gitlab-ci.yml

@@ -1,4 +1,8 @@
 include:
+  - project: "devops/gitlab/ci-templates/general"
+    file:
+      - ".install_hashicorp_vault.yml"
+      - ".vault_jwt_auth.yml"
   - project: "devops/gitlab/ci-templates/ruby"
     ref: "sans-dind"
     file:
@@ -37,19 +41,10 @@ gem_publication:
   image: ruby:3.2.2
   variables:
     GEMSPEC_FILE: "${CI_PROJECT_NAME}.gemspec"
-    VAULT_VERSION: "1.10.1"
+    VAULT_VERSION: "1.15.5"
   before_script:
-    - | 
-      apt-get update && apt-get -y install \
-      wget \
-      unzip && \
-      wget https://releases.hashicorp.com/vault/${VAULT_VERSION}/vault_${VAULT_VERSION}_linux_amd64.zip -O /tmp/vault_${VAULT_VERSION}.zip && \
-      unzip /tmp/vault_${VAULT_VERSION}.zip -d /usr/bin && \
-      rm -fr /tmp/vault_${VAULT_VERSION}.zip && \
-      apt-get remove -y wget unzip && \
-      apt-get clean
-    - export VAULT_ADDR=${VAULT_URL}
-    - export VAULT_TOKEN="$(vault write -field=token auth/jwt/${CI_SERVER_HOST}/login role=${JWT_ROLE} jwt=${CI_JOB_JWT})"
+    - !reference [.install_hashicorp_vault, before_script]
+    - !reference [.vault_jwt_auth, before_script]
     - export GEM_HOST_API_KEY="$(vault kv get -field=rubygems_api_key ${VAULT_KV_ENDPOINT}${ENVIRONMENT})"
     - |
       gem -v

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config --auto-gen-only-exclude --exclude-limit 10000`
-# on 2024-01-11 19:45:39 UTC using RuboCop version 1.51.0.
+# on 2024-01-17 17:00:02 UTC using RuboCop version 1.51.0.
 # 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
@@ -60,7 +60,7 @@ Metrics/CyclomaticComplexity:
     - 'lib/pennmarc/helpers/title.rb'
     - 'lib/pennmarc/util.rb'
 
-# Offense count: 25
+# Offense count: 26
 # Configuration parameters: CountComments, Max, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Exclude:

data/lib/pennmarc/enriched.rb

@@ -0,0 +1,93 @@
+# frozen_string_literal: true
+
+# Constants for Alma's MARC enrichment, performed and included in the MARCXML either by the Publishing process or by
+# API service
+module PennMARC
+  module Enriched
+    # Enriched MARC fields added by configurable setting in the Publishing profile that generates the MARCXML
+    # TODO: review if we can/should modify the subfields used in the pub profile to create parity with API subfields as
+    #       that could simplify this mapping tremendously
+    module Pub
+      # Enrichment Tag Names
+      PHYS_INVENTORY_TAG = 'hld'
+      ELEC_INVENTORY_TAG = 'prt'
+      ITEM_TAG = 'itm'
+
+      # Subfields for HLD tags
+      # Follow MARC 852 spec: https://www.loc.gov/marc/holdings/hd852.html, but names are translated into Alma parlance
+      PHYS_LOCATION_NAME = 'b' # e.g., Libra
+      PHYS_LOCATION_CODE = 'c' # e.g., stor
+      HOLDING_CLASSIFICATION_PART = 'h' # "classification part" first part of call num e.g., KF6450
+      HOLDING_ITEM_PART = 'i' # "item part?" second part of call num e.g., .C59 1989
+      PHYS_PUBLIC_NOTE = 'z'
+      PHYS_INTERNAL_NOTE = 'x'
+      PHYS_HOLDING_ID = '8'
+
+      # Subfields for ITM tags
+      ITEM_CURRENT_LOCATION = 'g'
+      ITEM_CALL_NUMBER_TYPE = 'h'
+      ITEM_CALL_NUMBER = 'i'
+      ITEM_DATE_CREATED = 'q'
+
+      # Subfields for PRT tags
+      ELEC_PORTFOLIO_ID = 'a'
+      ELEC_SERVICE_URL = 'b'
+      ELEC_COLLECTION_NAME = 'c'
+      ELEC_INTERFACE_NAME = 'e'
+      ELEC_PUBLIC_NOTE = 'f'
+      ELEC_COVERAGE_STMT = 'g'
+
+      # other values that could be added if we configured the Alma pub profile (and values are set on the record)
+      # - Authentication note
+      # - "static URL"
+      # - Electronic material type
+      # - Collection ID
+      # - create/update/activation date
+      # - license code
+      # - portfolio coverage info
+      #   - from year, until year (month, day volume issue)
+      # - portfolio embargo info
+      #   - years/months embargo'd
+
+      # TODO: evaluate this in context of changed boundwiths processing
+      # Franklin legacy note:
+      #   a subfield code NOT used by the MARC 21 spec for 852 holdings records.
+      #   we add this subfield during preprocessing to store boundwith record IDs.
+      # BOUND_WITH_ID = 'y'
+    end
+
+    # MARC enrichment originating from Alma API
+    # @see https://developers.exlibrisgroup.com/alma/apis/docs/bibs/R0VUIC9hbG1hd3MvdjEvYmlicy97bW1zX2lkfQ==/ Alma docs
+    # We cannot modify these subfield settings
+    module Api
+      # Enrichment Tag Names
+      PHYS_INVENTORY_TAG = 'AVA'
+      ELEC_INVENTORY_TAG = 'AVE'
+
+      # Physical Holding (AVA) subfields
+      PHYS_CALL_NUMBER = 'd'
+      PHYS_CALL_NUMBER_TYPE = 'k'
+      PHYS_LIBRARY_CODE = 'b'
+      PHYS_LIBRARY_NAME = 'q'
+      PHYS_LOCATION_CODE = 'j'
+      PHYS_LOCATION_NAME = 'c'
+      PHYS_HOLDING_ID = '8'
+      PHYS_AVAILABILITY = 'e'
+      PHYS_TOTAL_ITEMS = 'f'
+      PHYS_UNAVAILABLE_ITEMS = 'g'
+      PHYS_SUMMARY_INFO = 'v'
+      PHYS_PRIORITY = 'p'
+
+      # Electronic Portfolio (AVE) subfields
+      ELEC_LIBRARY_CODE = 'l'
+      ELEC_COLLECTION_NAME = 'm'
+      ELEC_PUBLIC_NOTE = 'n'
+      ELEC_SERVICE_URL = 'u'
+      ELEC_COVERAGE_STMT = 's'
+      ELEC_INTERFACE_NAME = 't'
+      ELEC_PORTFOLIO_ID = '8'
+      ELEC_COLLECTION_ID = 'c'
+      ELEC_ACTIVATION_STATUS = 'e'
+    end
+  end
+end

data/lib/pennmarc/helpers/access.rb

@@ -33,14 +33,14 @@ module PennMARC
       # @param [MARC::Field] field
       # @return [Boolean]
       def electronic_holding_tag?(field)
-        field.tag.in? [EnrichedMarc::TAG_ELECTRONIC_INVENTORY, EnrichedMarc::AlmaApi::TAG_ELECTRONIC_INVENTORY]
+        field.tag.in? [Enriched::Pub::ELEC_INVENTORY_TAG, Enriched::Api::ELEC_INVENTORY_TAG]
       end
 
       # Does the record have added physical holding info?
       # @param [MARC::Field] field
       # @return [Boolean]
       def physical_holding_tag?(field)
-        field.tag.in? [EnrichedMarc::TAG_HOLDING, EnrichedMarc::AlmaApi::TAG_PHYSICAL_INVENTORY]
+        field.tag.in? [Enriched::Pub::PHYS_INVENTORY_TAG, Enriched::Api::PHYS_INVENTORY_TAG]
       end
 
       # Check if a record contains an 856 entry for an online finding aid, meeting these criteria:

data/lib/pennmarc/helpers/citation.rb

@@ -11,9 +11,9 @@ module PennMARC
       # field 520 (Summary, Etc. Note).
       # https://www.loc.gov/marc/bibliographic/bd510.html
       # @param [MARC::Record] record
-      # @return [Array] array of citations and any linked alternates
+      # @return [Array<String>] array of citations and any linked alternates
       def cited_in_show(record)
-        datafield_and_linked_alternate(record, '510')
+        datafield_and_linked_alternate(record, '510').uniq
       end
 
       # Field 524 is the Preferred Citation of Described Materials Note. It is the Format for the citation of the
@@ -22,9 +22,9 @@ module PennMARC
       # introductory phrase that is generated as a display constant based on the first indicator value.
       # https://www.loc.gov/marc/bibliographic/bd524.html
       # @param [MARC::Record] record
-      # @return [Array] array of citation of described materials note and any linked alternates
+      # @return [Array<String>] array of citation of described materials note and any linked alternates
       def cite_as_show(record)
-        datafield_and_linked_alternate(record, '524')
+        datafield_and_linked_alternate(record, '524').uniq
       end
     end
   end

data/lib/pennmarc/helpers/classification.rb

@@ -16,19 +16,19 @@ module PennMARC
     }.freeze
 
     # Enriched MARC tags that hold classification data
-    TAGS = [EnrichedMarc::TAG_ITEM, EnrichedMarc::AlmaApi::TAG_PHYSICAL_INVENTORY].freeze
+    TAGS = [Enriched::Pub::ITEM_TAG, Enriched::Api::PHYS_INVENTORY_TAG].freeze
 
     class << self
       # Parse classification values for faceting. We retrieve classification values from enriched MARC fields 'itm' or
       # 'AVA' originating respectively from the Alma publishing process or from the Alma Api. We return the
       # highest level LOC or Dewey classifications from each available call number, joining the class code with
-      # its title in a single string. See {PennMARC::EnrichedMarc} and {PennMARC::EnrichedMarc::AlmaApi} for more
+      # its title in a single string. See {PennMARC::Enriched} and {PennMARC::Enriched::Api} for more
       # information on the enriched MARC fields.
       # @see https://developers.exlibrisgroup.com/alma/apis/docs/bibs/R0VUIC9hbG1hd3MvdjEvYmlicy97bW1zX2lkfQ==/ AVA docs
       # @param [MARC::Record] record
       # @return [Array<String>] array of classifications
       def facet(record)
-        record.fields(TAGS).flat_map do |field|
+        record.fields(TAGS).flat_map { |field|
           call_number_type = subfield_values(field, call_number_type_sf(field))&.first
           call_numbers = subfield_values(field, call_number_sf(field))
 
@@ -39,7 +39,7 @@ module PennMARC
 
             format_facet(class_code, call_number_type, title)
           end
-        end
+        }.uniq
       end
 
       private
@@ -48,18 +48,18 @@ module PennMARC
       # @param [MARC::DataField] field
       # @return [String]
       def call_number_sf(field)
-        return EnrichedMarc::SUB_ITEM_CALL_NUMBER if field.tag == EnrichedMarc::TAG_ITEM
+        return Enriched::Pub::ITEM_CALL_NUMBER if field.tag == Enriched::Pub::ITEM_TAG
 
-        EnrichedMarc::AlmaApi::SUB_PHYSICAL_CALL_NUMBER
+        Enriched::Api::PHYS_CALL_NUMBER
       end
 
       # Retrieve subfield code that stores call number type on enriched marc field
       # @param [MARC::DataField] field
       # @return [String]
       def call_number_type_sf(field)
-        return EnrichedMarc::SUB_ITEM_CALL_NUMBER_TYPE if field.tag == EnrichedMarc::TAG_ITEM
+        return Enriched::Pub::ITEM_CALL_NUMBER_TYPE if field.tag == Enriched::Pub::ITEM_TAG
 
-        EnrichedMarc::AlmaApi::SUB_PHYSICAL_CALL_NUMBER_TYPE
+        Enriched::Api::PHYS_CALL_NUMBER_TYPE
       end
 
       # retrieve title of classification based on single char classification code and call number type

data/lib/pennmarc/helpers/creator.rb

@@ -10,82 +10,43 @@ module PennMARC
     class << self
       # Main tags for Author/Creator information
       TAGS = %w[100 110].freeze
+
       # Aux tags for Author/Creator information, for use in search_aux method
       AUX_TAGS = %w[100 110 111 400 410 411 700 710 711 800 810 811].freeze
 
+      CONFERENCE_SEARCH_TAGS = %w[111 711 811].freeze
+
+      # subfields NOT to join when combining raw subfield values
+      NAME_EXCLUDED_SUBFIELDS = %w[a 1 4 5 6 8 t].freeze
+
       # Author/Creator search field. Includes all subfield values (even ǂ0 URIs) from
       # {https://www.oclc.org/bibformats/en/1xx/100.html 100 Main Entry--Personal Name} and
       # {https://www.oclc.org/bibformats/en/1xx/110.html 110 Main Entry--Corporate Name}. Maps any relator codes found
       # in ǂ4. To better handle name searches, returns names as both "First Last" and "Last, First" if a comma is found
-      # in ǂa. Also indexes any linked values in the 880. Some of the search fields remain incomplete and may need to be
-      # further investigated and ported when search result relevancy is considered.
-      # @todo this seems bad - why include relator labels? URIs? punctuation? leaving mostly as-is for now,
-      #       but this should be reexamined in the relevancy-tuning phase. URIs should def be removed. and shouldn't
-      #       indicator1 tell us the order of the name?
+      # in ǂa. Also indexes any linked values in the 880.
+      # @todo are we including too many details here and gumming up our index? consider UIRs, relator labels, dates...
+      # @todo shouldn't indicator1 tell us the order of the name? do we not trust the indicator?
       # @note ported from get_author_creator_1_search_values
       # @param [MARC::Record] record
       # @param [Hash] relator_map
       # @return [Array<String>] array of author/creator values for indexing
       def search(record, relator_map: Mappers.relator)
-        creator_subfields = %w[a 1 4 6 8]
-        acc = record.fields(TAGS).map do |field|
-          pieces = field.filter_map do |sf|
-            if sf.code == 'a'
-              convert_name_order(sf.value)
-            elsif creator_subfields.exclude?(sf.code)
-              sf.value
-            elsif sf.code == '4'
-              relator = translate_relator(sf.value, relator_map)
-              next if relator.blank?
-
-              relator
-            end
-          end
-          value = join_and_squish(pieces)
-          if value.end_with?('.', '-')
-            value
-          else
-            "#{value}."
-          end
-        end
-        # a second iteration over the same fields produces name entries with the names not reordered
-        secondary_subfields = %w[4 6 8]
-        acc += record.fields(TAGS).map do |field|
-          pieces = field.filter_map do |sf|
-            if secondary_subfields.exclude?(sf.code)
-              sf.value
-            elsif sf.code == '4'
-              relator = translate_relator(sf.value, relator_map)
-              next if relator.blank?
-
-              relator
-            end
-          end
-          value = join_and_squish(pieces)
-          if value.end_with?('.', '-')
-            value
-          else
-            "#{value}."
-          end
-        end
-        acc += record.fields(%w[880]).filter_map do |field|
-          next unless field.any? { |sf| sf.code == '6' && sf.value.in?(%w[100 110]) }
-
-          suba = field.find_all(&subfield_in?(%w[a])).map { |sf|
-            convert_name_order(sf.value)
-          }.first
-          oth = join_and_squish(field.find_all(&subfield_not_in?(%w[6 8 a t])).map(&:value))
-          join_and_squish [suba, oth]
-        end
-        acc.uniq
+        name_search_values record: record, tags: TAGS, relator_map: relator_map
       end
 
       # Auxiliary Author/Creator search field
+      # This duplicates the values returned by the search method, but adds in additional MARC tags to include
+      # creator-adjacent entities. The added 4xx tags are mostly obsolete, but the 7xx tags are important. See:
+      # {https://www.loc.gov/marc/bibliographic/bd700.html MARC 700},
+      # {https://www.loc.gov/marc/bibliographic/bd710.html MARC 710},
+      # and {https://www.loc.gov/marc/bibliographic/bd711.html MARC 711}. The 800, 810 and 8111 tags are similar in
+      # theme to the 7xx fields but apply to serial records.
       # @note ported from get_author_creator_2_search_values
-      # @todo port this later
       # @param [MARC::Record] record
       # @return [Array<String>] array of extended author/creator values for indexing
-      def search_aux(record); end
+      def search_aux(record, relator_map: Mappers.relator)
+        name_search_values record: record, tags: AUX_TAGS, relator_map: relator_map
+      end
 
       # All author/creator values for display (like #show, but multivalued?) - no 880 linkage
       # @note ported from get_author_creator_values (indexed as author_creator_a) - shown on results page
@@ -106,9 +67,9 @@ module PennMARC
       def show(record)
         fields = record.fields(TAGS)
         fields += record.fields('880').select { |field| subfield_value_in?(field, '6', TAGS) }
-        fields.filter_map do |field|
+        fields.filter_map { |field|
           join_subfields(field, &subfield_not_in?(%w[0 1 4 6 8 e w]))
-        end
+        }.uniq
       end
 
       # Author/Creator sort. Does not map and include any relator codes.
@@ -134,11 +95,11 @@ module PennMARC
           700 => 'abcdjq', 710 => 'abcdjq', 711 => 'abcen',
           800 => 'abcdjq', 810 => 'abcdjq', 811 => 'abcen'
         }
-        source_map.flat_map do |field_num, subfields|
+        source_map.flat_map { |field_num, subfields|
           record.fields(field_num.to_s).map do |field|
             trim_punctuation(join_subfields(field, &subfield_in?(subfields.chars)))
           end
-        end
+        }.uniq
       end
 
       # Conference for display, intended for results display
@@ -147,9 +108,9 @@ module PennMARC
       # @param [Hash] relator_map
       # @return [Array<String>] array of conference values
       def conference_show(record, relator_map: Mappers.relator)
-        record.fields('111').filter_map do |field|
+        record.fields('111').filter_map { |field|
           name_from_main_entry field, relator_map
-        end
+        }.uniq
       end
 
       # Conference detailed display, intended for record show page.
@@ -169,7 +130,7 @@ module PennMARC
           conf_extra = join_subfields field, &subfield_in?(%w[e j w])
           join_and_squish [conf, conf_extra].compact_blank
         end
-        values + record.fields('880').filter_map do |field|
+        conferences = values + record.fields('880').filter_map do |field|
           next unless subfield_value_in? field, '6', %w[111 711]
 
           next if subfield_defined? field, 'i'
@@ -178,11 +139,17 @@ module PennMARC
           conf_extra = join_subfields(field, &subfield_in?(%w[4 e j w]))
           join_and_squish [conf, conf_extra]
         end
+        conferences.uniq
       end
 
-      # @todo this supports "Conference" fielded search and may not be needed
-      # @note see get_conference_search_values
-      def conference_search(record); end
+      # Conference name values for searching
+      # @param [MARC::Record] record
+      # @return [Array<String>]
+      def conference_search(record)
+        record.fields(CONFERENCE_SEARCH_TAGS).filter_map { |field|
+          join_subfields(field, &subfield_in?(%w[a c d e]))
+        }.uniq
+      end
 
       # Retrieve contributor values for display from fields {https://www.oclc.org/bibformats/en/7xx/700.html 700}
       # and {https://www.oclc.org/bibformats/en/7xx/710.html 710} and their linked alternates. Joins subfields
@@ -193,7 +160,7 @@ module PennMARC
       # @return [Array<String>]
       def contributor_show(record, relator_map: Mappers.relator)
         indicator_2_options = ['', ' ', '0']
-        contributors = record.fields(%w[700 710]).filter_map do |field|
+        values = record.fields(%w[700 710]).filter_map do |field|
           next unless indicator_2_options.member?(field.indicator2)
           next if subfield_defined? field, 'i'
 
@@ -210,7 +177,7 @@ module PennMARC
           }.join
           "#{contributor} #{contributor_append}".squish
         end
-        contributors + record.fields('880').filter_map do |field|
+        contributors = values + record.fields('880').filter_map do |field|
           next unless subfield_value_in?(field, '6', %w[700 710])
           next if subfield_defined?(field, 'i')
 
@@ -218,10 +185,37 @@ module PennMARC
           contributor_append = join_subfields(field, &subfield_in?(%w[e u 3]))
           "#{contributor} #{contributor_append}".squish
         end
+        contributors.uniq
       end
 
       private
 
+      # @param [MARC::Record] record
+      # @param [Array] tags to consider
+      # @param [Hash] relator_map
+      # @return [Array<String>] name values from given tags
+      def name_search_values(record:, tags:, relator_map:)
+        acc = record.fields(tags).filter_map do |field|
+          name_from_main_entry field, relator_map, should_convert_name_order: false
+        end
+
+        acc += record.fields(tags).filter_map do |field|
+          name_from_main_entry field, relator_map, should_convert_name_order: true
+        end
+
+        acc += record.fields(['880']).filter_map do |field|
+          next unless field.any? { |sf| sf.code == '6' && sf.value.in?(tags) }
+
+          suba = field.find_all(&subfield_in?(%w[a])).filter_map { |sf|
+            convert_name_order(sf.value)
+          }.first
+          oth = join_and_squish(field.find_all(&subfield_not_in?(%w[6 8 a t])).map(&:value))
+          join_and_squish [suba, oth]
+        end
+
+        acc.uniq
+      end
+
       # Trim punctuation method extracted from Traject macro, to ensure consistent output
       # @todo move to Util?
       # @param [String] string
@@ -244,11 +238,14 @@ module PennMARC
 
       # Extract the information we care about from 1xx fields, map relator codes, and use appropriate punctuation
       # @param [MARC::Field] field
+      # @param [Hash] mapping
+      # @param [Boolean] should_convert_name_order
       # @return [String] joined subfield values for value from field
-      def name_from_main_entry(field, mapping)
-        name_subfields = %w[0 1 4 6 8]
+      def name_from_main_entry(field, mapping, should_convert_name_order: false)
         s = field.filter_map { |sf|
-          if name_subfields.exclude?(sf.code)
+          if sf.code == 'a'
+            should_convert_name_order ? convert_name_order(sf.value) : sf.value
+          elsif NAME_EXCLUDED_SUBFIELDS.exclude?(sf.code)
             " #{sf.value}"
           elsif sf.code == '4'
             relator = translate_relator(sf.value, mapping)

data/lib/pennmarc/helpers/database.rb

@@ -19,13 +19,13 @@ module PennMARC
       # @param [Marc::Record]
       # @return [Array<string>] Array of types
       def type_facet(record)
-        record.fields('944').filter_map do |field|
+        record.fields('944').filter_map { |field|
           # skip unless specified database format type present
           next unless subfield_value?(field, 'a', /#{DATABASES_FACET_VALUE}/o)
 
           type = field.find { |subfield| subfield.code == 'b' }
           type&.value
-        end
+        }.uniq
       end
 
       # Retrieves database subject category/communities of interest (subfield 'a') from
@@ -37,13 +37,13 @@ module PennMARC
       def category_facet(record)
         return [] unless curated_db?(record)
 
-        record.fields('943').filter_map do |field|
+        record.fields('943').filter_map { |field|
           # skip unless Community of Interest code is in subfield '2'
           next unless subfield_value?(field, '2', /#{COI_CODE}/o)
 
           category = field.find { |subfield| subfield.code == 'a' }
           category&.value
-        end
+        }.uniq
       end
 
       # Concatenates database subject category with database sub subject category in the format "category--subcategory"
@@ -58,7 +58,7 @@ module PennMARC
       def subcategory_facet(record)
         return [] unless curated_db?(record)
 
-        record.fields('943').filter_map do |field|
+        record.fields('943').filter_map { |field|
           # skip unless Community of Interest code is in subfield '2'
           next unless subfield_value?(field, '2', /#{COI_CODE}/o)
 
@@ -73,7 +73,7 @@ module PennMARC
           next if subcategory.blank?
 
           "#{category.value}--#{subcategory.value}"
-        end
+        }.uniq
       end
 
       private

data/lib/pennmarc/helpers/date.rb

@@ -20,13 +20,13 @@ module PennMARC
       end
 
       # Retrieve date added (subfield 'q') from enriched marc 'itm' field.
-      # {PennMARC::EnrichedMarc} maps enriched marc fields and subfields created during Alma publishing. The enriched
+      # {PennMARC::Enriched} maps enriched marc fields and subfields created during Alma publishing. The enriched
       # metadata provided by the Alma API does not include the date created value, so we can't work with that here.
       # @param [MARC::Record] record
       # @return [DateTime, nil] The date added, or nil if date found in record is invalid
       def added(record)
-        record.fields(EnrichedMarc::TAG_ITEM).flat_map { |field|
-          subfield_values(field, EnrichedMarc::SUB_ITEM_DATE_CREATED).filter_map do |date_added|
+        record.fields(Enriched::Pub::ITEM_TAG).flat_map { |field|
+          subfield_values(field, Enriched::Pub::ITEM_DATE_CREATED).filter_map do |date_added|
             # On 2022-05-02, this field value (as exported in enriched publishing
             # job from Alma) began truncating time to day-level granularity. We have
             # no guarantee that this won't switch back in the future, so for the

data/lib/pennmarc/helpers/edition.rb

@@ -14,9 +14,10 @@ module PennMARC
       # @param [MARC::Record] record
       # @return [Array<String>] array of editions and their alternates
       def show(record)
-        record.fields('250').map { |field|
+        editions = record.fields('250').map { |field|
           join_subfields(field, &subfield_not_in?(%w[6 8]))
         } + linked_alternate_not_6_or_8(record, '250')
+        editions.uniq
       end
 
       # Edition values for display in search results. Just grab the first 250 field.
@@ -42,12 +43,13 @@ module PennMARC
 
           other_edition_value(field, relator_map)
         end
-        values + record.fields('880').filter_map do |field|
+        editions = values + record.fields('880').filter_map do |field|
           next unless field.indicator2.blank? && subfield_value_in?(field, '6', %w[775]) &&
                       subfield_defined?(field, 'i')
 
           other_edition_value(field, relator_map)
         end
+        editions.uniq
       end
 
       private

data/lib/pennmarc/helpers/format.rb

@@ -48,7 +48,7 @@ module PennMARC
                                end
           join_subfields(f, &subfield_not_in?(subfield_to_ignore))
         end
-        results.compact_blank
+        results.compact_blank.uniq
       end
 
       # Get Format values for faceting. Format values are determined using complex logic for each possible format value.
@@ -122,23 +122,24 @@ module PennMARC
                        OTHER
                      end
         end
-        formats.concat(curated_format(record))
+        formats.concat(curated_format(record)).uniq
       end
 
       # Show "Other Format" values from {https://www.oclc.org/bibformats/en/7xx/776.html 776} and any 880 linkage.
       # @todo is 774 an error in the linked field in legacy? i changed to 776 here
       # @param [MARC::Record] record
-      # @return [Array] other format values for display
+      # @return [Array<String>] other format values for display
       def other_show(record)
-        other_formats = record.fields('776').filter_map do |field|
+        values = record.fields('776').filter_map do |field|
           value = join_subfields(field, &subfield_in?(%w[i a s t o]))
           next if value.blank?
 
           value
         end
-        other_formats + linked_alternate(record, '776') do |sf|
+        other_formats = values + linked_alternate(record, '776') do |sf|
           sf.code.in? %w[i a s t o]
         end
+        other_formats.uniq
       end
 
       # Retrieve cartographic reference data for map/atlas formats for display from
@@ -146,9 +147,9 @@ module PennMARC
       # @param [MARC::Record] record
       # @return [Array<String>]
       def cartographic_show(record)
-        record.fields(%w[255 342]).map do |field|
+        record.fields(%w[255 342]).map { |field|
           join_subfields(field, &subfield_not_in?(%w[6 8]))
-        end
+        }.uniq
       end
 
       # Check if a set of locations has any locations that include the term 'manuscripts'
@@ -165,14 +166,14 @@ module PennMARC
       # @param [MARC::Record] record
       # @return [Array]
       def call_nums(record)
-        if field_defined?(record, EnrichedMarc::TAG_HOLDING)
-          record.fields(EnrichedMarc::TAG_HOLDING).map do |field|
-            join_subfields(field, &subfield_in?([EnrichedMarc::SUB_HOLDING_CLASSIFICATION_PART,
-                                                 EnrichedMarc::SUB_HOLDING_ITEM_PART]))
+        if field_defined?(record, Enriched::Pub::PHYS_INVENTORY_TAG)
+          record.fields(Enriched::Pub::PHYS_INVENTORY_TAG).map do |field|
+            join_subfields(field, &subfield_in?([Enriched::Pub::HOLDING_CLASSIFICATION_PART,
+                                                 Enriched::Pub::HOLDING_ITEM_PART]))
           end
-        elsif field_defined?(record, EnrichedMarc::AlmaApi::TAG_PHYSICAL_INVENTORY)
-          record.fields(EnrichedMarc::AlmaApi::TAG_PHYSICAL_INVENTORY).map do |field|
-            join_subfields(field, &subfield_in?([EnrichedMarc::AlmaApi::SUB_PHYSICAL_CALL_NUMBER_TYPE]))
+        elsif field_defined?(record, Enriched::Api::PHYS_INVENTORY_TAG)
+          record.fields(Enriched::Api::PHYS_INVENTORY_TAG).map do |field|
+            join_subfields(field, &subfield_in?([Enriched::Api::PHYS_CALL_NUMBER_TYPE]))
           end
         else
           []