pennmarc 1.4.9 → 1.4.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2ee4c96f758d430badc9594ba3b31ad1abd2d8b5b92f80cd681fe4fbe053a21a
-  data.tar.gz: 0a28c912baed15e8e5e50256ebd61b7225af8724f1291c84ab5ac9d4a25f8006
+  metadata.gz: ed8428b56d9ed1e81912885aef968ba0f104f647491afd2498e4e3893748b9c4
+  data.tar.gz: fead988cff9b7cb56201510a7eba63152dd16f8e691ece753d6b306158afc53e
 SHA512:
-  metadata.gz: 8afaa2eea826782c1390c6691ed32d9475a8263c7155239e820dcb0d1ed99bef861151b676f58cf006fa6999eb1dffb582700d74141167f9b44edfb65a99d249
-  data.tar.gz: c05fa58a6e4a3ba45ebb6844182c2dd938bd15f7dcd055a1a2a0ae212fac99fc7529724f691b8a8abcd6d37a41eab42f1491325860178f9bab675f9498c944ff
+  metadata.gz: 21e44d07cd4bde553e717f84a944dd297055f94518a27a14f9d9fb3d64c3f1f9172746af0ba0d9e1549fb69198a7ef5f5c23b5323189bba500d04cc5ace40a32
+  data.tar.gz: caaf7925c9d91833c92ba25524dc70f4bad6f4b31c7640ff35823f20477d5d9c7b7449770bd8ffdcd66fde1a39460ddbad58666d71eeeb22ca3b225f5da72d9a

data/.gitlab/ci-requirements.yml

@@ -0,0 +1,17 @@
+---
+collections:
+  - name: "https://gitlab.library.upenn.edu/api/v4/projects/devops%2Fansible%2Fcollection\
+      /packages/generic/collections/stack-v2.2.0/library-stack-2.2.0.tar.gz"
+    type: url
+  - name: "https://gitlab.library.upenn.edu/api/v4/projects/devops%2Fansible%2Fcollection\
+      /packages/generic/collections/proxmox-v1.6.0/library-proxmox-1.6.0.tar.gz"
+    type: url
+  - name: "https://gitlab.library.upenn.edu/api/v4/projects/devops%2Fansible%2Fcollection\
+      /packages/generic/collections/services-v1.11.0/library-services-1.11.0.tar.gz"
+    type: url
+  - name: "https://gitlab.library.upenn.edu/api/v4/projects/devops%2Fansible%2Fcollection\
+      /packages/generic/collections/infra-v4.7.0/library-infra-4.7.0.tar.gz"
+    type: url
+  - name: "https://gitlab.library.upenn.edu/api/v4/projects/devops%2Fansible%2Fcollection\
+      /packages/generic/collections/ci-v0.7.0/library-ci-0.7.0.tar.gz"
+    type: url

data/.gitlab-ci.yml

@@ -1,34 +1,102 @@
 ---
+variables:
+  FF_SCRIPT_SECTIONS: "true"
+
 include:
-  - template: Jobs/Secret-Detection.gitlab-ci.yml
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/sast/secret_scan@~latest
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/install_ansible@~latest
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/ci_requirements@~latest
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/install_hashicorp_vault@~latest
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/vault_jwt_auth@~latest
+    inputs:
+      ci_requirements_file: ".gitlab/ci-requirements.yml"
+      vault_addr: ${VAULT_ADDR}
+      vault_auth_path: ${VAULT_AUTH_PATH}
+      vault_auth_role: ${VAULT_AUTH_ROLE}
+  - component: gitlab.library.upenn.edu/devops/gitlab/components/tests/rubocop@~latest
+    inputs:
+      app_dir: "."
+      job_image_name: "ruby"
+      job_image_tag: "3.2.2"
+      needs:
+        - secret_detection
 
 stages:
   - secret_check
-  - main_pipeline
+  - test
+  - deploy
+
+rubocop:
+  before_script:
+    - bundle install -j $(nproc)
+  rules:
+    - exists:
+        - .rubocop.yml
 
-secret_detection:
-  stage: secret_check
-  allow_failure: false
+rspec:
+  stage: test
+  image: ruby:3.2.2
+  needs:
+    - secret_detection
+  variables:
+    ANSIBLE_COLLECTIONS_CACHE_DIR: .cache/ansible/collections
+    GALAXY_REQUIREMENTS_FILE: ".gitlab/ci-requirements.yml"
+  cache:
+    - key:
+        files:
+          - .gitlab/ci-requirements.yml
+        prefix: ansible-collections
+      paths:
+        - $ANSIBLE_COLLECTIONS_CACHE_DIR
+  before_script:
+    - !reference [.install_ansible, before_script]
+    - !reference [.ci_requirements, before_script]
+    - bundle install -j $(nproc)
+  script:
+    - tail -F --pid=$$ rspec.log 2>/dev/null &
+    - ansible-playbook library.ci.rails_test -e rails_test_app_dir="."
   artifacts:
     paths:
-      - .pipeline.yml
-    expire_in: 1 day
+      - rspec.xml
+    expire_in: 1 week
+    reports:
+      junit: rspec.xml
+  rules:
+    - exists:
+        - spec/**.rb
+        - spec/**/**.rb
   tags:
     - build
-  rules:
-  - when: always
 
-main:
-  stage: main_pipeline
-  needs:
-    - secret_detection
-  allow_failure: false
-  trigger:
-    include:
-      - artifact: .pipeline.yml
-        job: secret_detection
-    strategy: depend
+# This step was inspired from Gitlab's example of gem publication:
+# https://gitlab.com/gitlab-org/quality/pipeline-common/-/blob/master/ci/gem-release.yml
+gem_publication:
+  stage: deploy
+  image: ruby:3.2.2
+  extends:
+    - .vault_jwt_auth
+  variables:
+    GEMSPEC_FILE: "${CI_PROJECT_NAME}.gemspec"
+  before_script:
+    - !reference [.install_ansible, before_script]
+    - !reference [.install_hashicorp_vault, before_script]
+    - !reference [.vault_jwt_auth, before_script]
+  script:
+    - export GEM_HOST_API_KEY="$(vault kv get -field=rubygems_api_key ${VAULT_KV_ENDPOINT}${ENVIRONMENT})"
+    - |
+      gem -v
+      rm -f ./*.gem
+      [ -f "${GEMSPEC_FILE}" ] || (echo "No ${GEMSPEC_FILE} file found!" && exit 1)
+    - '[ -n "${GEM_HOST_API_KEY}" ] || (echo "GEM_HOST_API_KEY is not set!" && exit 1)'
+    - GEM_FILE=$(echo "${CI_PROJECT_NAME}-${CI_COMMIT_TAG:1}.gem")
+    - |
+      gem build "${GEMSPEC_FILE}"
+      [ -f "${GEM_FILE}" ] || (echo "No ${GEM_FILE} file found!" && exit 1)
+    - '[ "${DISABLE_GEM_PUSH}" == "true" ] || gem push "${GEM_FILE}"'
   rules:
-  - if: "$CI_MERGE_REQUEST_IID"
-  - if: "$CI_COMMIT_TAG"
-  - if: "$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH"
+    - if: $CI_COMMIT_TAG =~ /^v\d+\.\d+\.\d+(\.[a-zA-Z0-9]+)?$/
+  artifacts:
+    paths:
+      - "*.gem"
+  tags:
+    - deploy

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 2025-10-22 21:06:47 UTC using RuboCop version 1.79.2.
+# on 2026-09-28 22:29:36 UTC using RuboCop version 1.84.1.
 # 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
@@ -33,7 +33,7 @@ Metrics/ClassLength:
     - 'lib/pennmarc/helpers/subject.rb'
     - 'lib/pennmarc/helpers/title.rb'
 
-# Offense count: 22
+# Offense count: 23
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Exclude:
@@ -70,7 +70,7 @@ Metrics/ModuleLength:
   Exclude:
     - 'lib/pennmarc/util.rb'
 
-# Offense count: 17
+# Offense count: 18
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Exclude:
@@ -82,6 +82,7 @@ Metrics/PerceivedComplexity:
     - 'lib/pennmarc/helpers/note.rb'
     - 'lib/pennmarc/helpers/production.rb'
     - 'lib/pennmarc/helpers/series.rb'
+    - 'lib/pennmarc/helpers/subject.rb'
     - 'lib/pennmarc/helpers/title.rb'
     - 'lib/pennmarc/util.rb'
 
@@ -109,18 +110,16 @@ RSpec/ExampleLength:
   Exclude:
     - 'spec/lib/pennmarc/marc_util_spec.rb'
 
+# Offense count: 1
+# Configuration parameters: AllowSubject, Max.
+RSpec/MultipleMemoizedHelpers:
+  Exclude:
+    - 'spec/lib/pennmarc/helpers/subject_spec.rb'
+
 # Offense count: 2
-# Configuration parameters: Include, CustomTransform, IgnoreMethods, IgnoreMetadata.
-# Include: **/*_spec.rb
+# Configuration parameters: CustomTransform, IgnoreMethods, IgnoreMetadata, InflectorPath, EnforcedInflector.
+# SupportedInflectors: default, active_support
 RSpec/SpecFilePathFormat:
   Exclude:
     - 'spec/lib/pennmarc/parser_spec.rb'
     - 'spec/lib/pennmarc/services/title_suggestion_weight_service_spec.rb'
-
-# Offense count: 1
-# This cop supports unsafe autocorrection (--autocorrect-all).
-# Configuration parameters: EnforcedStyle, AllowedMethods, AllowedPatterns.
-# SupportedStyles: predicate, comparison
-Style/NumericPredicate:
-  Exclude:
-    - 'lib/pennmarc/services/title_suggestion_weight_service.rb'

data/README.md

@@ -93,7 +93,19 @@ rspec
    2. Create a new tag that matches the version set in step 1 (ex: v1.1.0). 
    3. Add a release title that is the same as the tag name. 
    4. Submit by clicking "Create Release".
-4. Once the release is created a pipeline will run to publish the gem to RubyGems. 
+4. Once the release is created a pipeline will run to publish the gem to RubyGems.
+
+### Publishing Manually
+
+You can also publish the gem using `gem` commands. After updating the `VERSION` value on `main`, you can run the
+following commands:
+
+```bash
+gem build pennmarc.gemspec
+gem push pennmarc-<VERSION>.gem
+```
+
+You may need an OTP code for use in the push to bundler.
 
 ### Versioning Guidelines
 

data/lib/pennmarc/heading_control.rb

@@ -5,28 +5,36 @@ module PennMARC
   class HeadingControl
     # These codes are expected to be found in sf2 of a subject/genre field when the indicator2 value is 7, indicating
     # "source specified". There are some sources whose headings we don't want to display.
-    ALLOWED_SOURCE_CODES = %w[aat cct fast ftamc gmgpc gsafd homoit jlabsh lcgft lcsh lcstt lctgm
+    ALLOWED_SOURCE_CODES = %w[aat cct fast ftamc gmgpc gsafd homoit homoit/eng jlabsh lcgft lcsh lcstt lctgm local/upenn
                               local/osu mesh ndlsh nli nlksh rbbin rbgenr rbmscv rbpap rbpri rbprov rbpub rbtyp].freeze
 
     REMOVE_TERM_REGEX = /#{Mappers.headings_to_remove&.join('|')}/i
     REPLACE_TERM_REGEX = /(#{Mappers.heading_overrides.keys.join('|')})/i
 
+    # Don't perform any term overriding on these tags
+    NO_OVERRIDE_TAGS = %w[600 610 611 630].freeze
+
     class << self
       # Replace or remove any terms in provided values pursuant to the configuration in remove and override mappers.
       # Used to remove or replace offensive or otherwise undesirable subject headings.
-      # @param values [Array]
-      # @return [Array] values with terms removed/replaced
-      def term_override(values)
-        values.filter_map do |value|
-          # Remove values if they contain a remove term
-          next nil if value.match?(REMOVE_TERM_REGEX)
+      # @param [String] value
+      # @return [String, nil]
+      def term_override(value)
+        # Remove values if they contain a remove term
+        return if value.match?(REMOVE_TERM_REGEX)
+
+        # return early if there are no terms to replace
+        return value if value.match(REPLACE_TERM_REGEX).nil?
 
-          # return early if theres no terms to replace
-          next value if value.match(REPLACE_TERM_REGEX).nil?
+        # lookup and perform replacement
+        value.sub(::Regexp.last_match.to_s, Mappers.heading_overrides[::Regexp.last_match.to_s.downcase])
+      end
 
-          # lookup and perform replacement
-          value.sub(::Regexp.last_match.to_s, Mappers.heading_overrides[::Regexp.last_match.to_s.downcase])
-        end
+      # Is the given field overrideable?
+      # @param field [MARC::Field]
+      # @return [Boolean]
+      def overrideable_field?(field)
+        !field.tag.in?(NO_OVERRIDE_TAGS)
       end
     end
   end

data/lib/pennmarc/helpers/creator.rb

@@ -9,10 +9,10 @@ module PennMARC
     TAGS = %w[100 110].freeze
 
     # For creator fields intended for display, these subfields are ignored
-    DISPLAY_EXCLUDED_SUBFIELDS = %w[a 0 1 4 5 6 8 t].freeze
+    DISPLAY_EXCLUDED_SUBFIELDS = %w[a 0 1 4 5 6 7 8 t].freeze
 
     # For creator fields intended for searching, these subfields are ignored
-    SEARCH_EXCLUDED_SUBFIELDS = %w[a 1 4 5 6 8 t].freeze
+    SEARCH_EXCLUDED_SUBFIELDS = %w[a 1 4 5 6 7 8 t].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
@@ -23,6 +23,8 @@ module PennMARC
     CONTRIBUTOR_TAGS = %w[700 710].freeze
     CONTRIBUTOR_DISPLAY_SUBFIELDS = %w[a b c d j q u 3].freeze
 
+    UNIVERSITY_IDENTIFIER = 'PU'
+
     FACET_SOURCE_MAP = {
       100 => 'abcdjq', 110 => 'abcdjq', 111 => 'abcen',
       700 => 'abcdjq', 710 => 'abcdjq', 711 => 'abcen',
@@ -33,7 +35,7 @@ module PennMARC
       # Author/Creator search field, from tags
       # {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}. Includes subfield values
-      # except for those in the {DISPLAY_EXCLUDED_SUBFIELDS} constant. Maps any relator codes found in ǂ4. To better
+      # except for those in the {SEARCH_EXCLUDED_SUBFIELDS} constant. 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.
       # @param record [MARC::Record]
@@ -127,6 +129,8 @@ module PennMARC
       def authors_list(record, main_tags_only: false, first_initial_only: false)
         fields = record.fields(main_tags_only ? TAGS : TAGS + CONTRIBUTOR_TAGS)
         fields.filter_map { |field|
+          next if university_provenance? field
+
           if field['a'].present?
             name = trim_trailing(:comma, field['a'])
             first_initial_only ? abbreviate_name(name) : name
@@ -153,6 +157,7 @@ module PennMARC
         fields.each do |field|
           next if indicator_2_options.exclude?(field.indicator2) && field.tag.in?(CONTRIBUTOR_TAGS)
           next if subfield_defined? field, 'i'
+          next if university_provenance? field
 
           relator = relator(field: field, relator_term_sf: 'e', relator_map: relator_map)
           relator = 'Contributor' if relator.blank?
@@ -458,7 +463,7 @@ module PennMARC
       # @param relator_map [Hash]
       # @return [String]
       def parse_show_value(field, relator_map: Mappers.relator)
-        creator = join_subfields(field, &subfield_not_in?(%w[0 1 4 6 8 e w]))
+        creator = join_subfields(field, &subfield_not_in?(%w[0 1 4 6 7 8 e w]))
         append_relator(field: field, joined_subfields: creator, relator_term_sf: 'e', relator_map: relator_map)
       end
 
@@ -470,7 +475,7 @@ module PennMARC
       # @return [String]
       def parse_conference_detail_show_value(field, relator_map: Mappers.relator)
         conf = if subfield_undefined? field, 'i'
-                 join_subfields field, &subfield_not_in?(%w[0 4 5 6 8 e j w])
+                 join_subfields field, &subfield_not_in?(%w[0 4 5 6 7 8 e j w])
                else
                  ''
                end
@@ -486,6 +491,14 @@ module PennMARC
       def describes_author?(field)
         field['4']&.downcase == 'aut' || field['e']&.downcase&.start_with?('author')
       end
+
+      # Does the given field describe a contributor representing university provenance. A contributor tag with a '$5'
+      # value equal to the university identifier represents university provenance.
+      # @param field [MARC::Field]
+      # @return [Boolean]
+      def university_provenance?(field)
+        field.tag.in?(CONTRIBUTOR_TAGS) && subfield_values(field, '5').include?(UNIVERSITY_IDENTIFIER)
+      end
     end
   end
 end

data/lib/pennmarc/helpers/edition.rb

@@ -16,7 +16,7 @@ module PennMARC
       # @return [Array<String>] array of editions and their alternates
       def show(record, with_alternate: true)
         editions = record.fields('250').map do |field|
-          join_subfields(field, &subfield_not_in?(%w[6 8]))
+          join_subfields(field, &subfield_not_in?(%w[6 7 8]))
         end
         editions += linked_alternate_not_6_or_8(record, '250') if with_alternate
 
@@ -30,7 +30,7 @@ module PennMARC
         edition = record.fields('250').first
         return if edition.blank?
 
-        join_subfields(edition, &subfield_not_in?(%w[6 8]))
+        join_subfields(edition, &subfield_not_in?(%w[6 7 8]))
       end
 
       # Entry for another available edition of the target item (horizontal relationship). When a note is generated

data/lib/pennmarc/helpers/format.rb

@@ -38,7 +38,7 @@ module PennMARC
       def show(record)
         results = record.fields('300').map { |f| join_subfields(f, &subfield_not_in?(%w[3 6 8])) }
         results += record.fields(%w[254 255 310 342 352 362]).map do |f|
-          join_subfields(f, &subfield_not_in?(%w[6 8]))
+          join_subfields(f, &subfield_not_in?(%w[6 7 8]))
         end
         results += record.fields('340').map { |f| join_subfields(f, &subfield_not_in?(%w[0 2 6 8])) }
         results += record.fields('880').map do |f|

data/lib/pennmarc/helpers/language.rb

@@ -16,7 +16,7 @@ module PennMARC
       # @return [Array<String>] language values and notes
       def show(record)
         values = record.fields('546').map do |field|
-          join_subfields field, &subfield_not_in?(%w[6 8])
+          join_subfields field, &subfield_not_in?(%w[6 7 8])
         end
         language_values = values + linked_alternate(record, '546', &subfield_not_in?(%w[6 8]))
         language_values.uniq

data/lib/pennmarc/helpers/subject.rb

@@ -7,25 +7,25 @@ module PennMARC
   # tightly to be preserved. As a result fo this, display methods and facet methods below are ported from their state
   # prior to Michael's 2/2021 subject parsing changes.
   class Subject < Helper
-    class << self
-      # Tags that serve as sources for Subject search values
-      # @todo why are 541 and 561 included here? these fields include info about source of acquisition
-      SEARCH_TAGS = %w[541 561 600 610 611 630 650 651 653].freeze
+    # Tags that serve as sources for Subject search values
+    # @todo why are 541 and 561 included here? these fields include info about source of acquisition
+    SEARCH_TAGS = %w[541 561 600 610 611 630 650 651 653].freeze
 
-      # Valid indicator 2 values indicating the source thesaurus for subject terms. These are:
-      # - 0: LCSH
-      # - 1: LC Children's
-      # - 2: MeSH
-      # - 4: Source not specified (local?)
-      # - 7: Source specified in ǂ2
-      VALID_SOURCE_INDICATORS = %w[0 1 2 4 7].freeze
+    # Valid indicator 2 values indicating the source thesaurus for subject terms. These are:
+    # - 0: LCSH
+    # - 1: LC Children's
+    # - 2: MeSH
+    # - 4: Source not specified (local?)
+    # - 7: Source specified in ǂ2
+    VALID_SOURCE_INDICATORS = %w[0 1 2 4 7].freeze
 
-      # Tags that serve as sources for Subject facet values
-      DISPLAY_TAGS = %w[600 610 611 630 650 651].freeze
+    # Tags that serve as sources for Subject facet values
+    DISPLAY_TAGS = %w[600 610 611 630 650 651].freeze
 
-      # Local subject heading tags
-      LOCAL_TAGS = %w[690 691 697].freeze
+    # Local subject heading tags
+    LOCAL_TAGS = %w[690 691 697].freeze
 
+    class << self
       # All Subjects for searching. This includes most subfield content from any field contained in {SEARCH_TAGS} or
       # 69X, including any linked 880 fields. Fields must have an indicator2 value in {VALID_SOURCE_INDICATORS}.
       # @todo this includes subfields that may not be desired like 1 (uri) and 2 (source code) but this might be OK for
@@ -63,11 +63,11 @@ module PennMARC
       #
       # @note this is ported mostly form MG's new-style Subject parsing
       # @param record [MARC::Record]
-      # @param override [Boolean] remove undesirable terms or not
+      # @param override [Boolean] whether to remove undesirable terms in eligible fields or not
       # @return [Array<String>] array of all subject values for faceting
       def facet(record, override: true)
-        values = subject_fields(record, type: :facet).filter_map { |field|
-          term_hash = build_subject_hash(field)
+        subject_fields(record, type: :facet).filter_map { |field|
+          term_hash = build_subject_hash(field, override)
           next if term_hash.blank? || term_hash[:count]&.zero?
 
           heading = format_term type: :facet, term: term_hash
@@ -75,8 +75,6 @@ module PennMARC
 
           [heading, main_term].compact_blank
         }.flatten.uniq
-
-        override ? HeadingControl.term_override(values) : values
       end
 
       # All Subjects for display. This includes all {DISPLAY_TAGS} and {LOCAL_TAGS}. For tags that specify a source,
@@ -87,8 +85,8 @@ module PennMARC
       # @param override [Boolean] to remove undesirable terms or not
       # @return [Array] array of all subject values for display
       def show(record, override: true)
-        values = subject_fields(record, type: :all).filter_map { |field|
-          term_hash = build_subject_hash(field)
+        subject_fields(record, type: :all).filter_map { |field|
+          term_hash = build_subject_hash(field, override)
           next if term_hash.blank? || term_hash[:count]&.zero?
 
           heading = format_term type: :display, term: term_hash
@@ -96,7 +94,6 @@ module PennMARC
 
           [heading, main_term].compact_blank
         }.flatten.uniq
-        override ? HeadingControl.term_override(values) : values
       end
 
       # Get Subjects from "Children" ontology
@@ -105,14 +102,13 @@ module PennMARC
       # @param override [Boolean] remove undesirable terms or not
       # @return [Array] array of children's subject values for display
       def childrens_show(record, override: true)
-        values = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '1' })
-                 .filter_map { |field|
-                   term_hash = build_subject_hash(field)
-                   next if term_hash.blank? || term_hash[:count]&.zero?
+        subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '1' })
+          .filter_map { |field|
+            term_hash = build_subject_hash(field, override)
+            next if term_hash.blank? || term_hash[:count]&.zero?
 
-                   format_term type: :display, term: term_hash
+            format_term type: :display, term: term_hash
         }.uniq
-        override ? HeadingControl.term_override(values) : values
       end
 
       # Get Subjects from "MeSH" ontology
@@ -121,14 +117,13 @@ module PennMARC
       # @param override [Boolean] remove undesirable terms or not
       # @return [Array] array of MeSH subject values for display
       def medical_show(record, override: true)
-        values = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '2' })
-                 .filter_map { |field|
-                   term_hash = build_subject_hash(field)
-                   next if term_hash.blank? || term_hash[:count]&.zero?
+        subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '2' })
+          .filter_map { |field|
+            term_hash = build_subject_hash(field, override)
+            next if term_hash.blank? || term_hash[:count]&.zero?
 
-                   format_term type: :display, term: term_hash
+            format_term type: :display, term: term_hash
         }.uniq
-        override ? HeadingControl.term_override(values) : values
       end
 
       # Get Subject values from {DISPLAY_TAGS} where indicator2 is 4 and {LOCAL_TAGS}. Do not include any values where
@@ -140,15 +135,14 @@ module PennMARC
       def local_show(record, override: true)
         local_fields = subject_fields(record, type: :display, options: { tags: DISPLAY_TAGS, indicator2: '4' }) +
                        subject_fields(record, type: :local)
-        values = local_fields.filter_map { |field|
+        local_fields.filter_map { |field|
           next if subfield_value?(field, '2', /penncoi/)
 
-          term_hash = build_subject_hash(field)
+          term_hash = build_subject_hash(field, override)
           next if term_hash.blank? || term_hash[:count]&.zero?
 
           format_term type: :display, term: term_hash
         }.uniq
-        override ? HeadingControl.term_override(values) : values
       end
 
       private
@@ -177,25 +171,26 @@ module PennMARC
         end
       end
 
-      # Format a term hash as a string for display
+      # Format a term hash as a string for display, performing overrides if needed
       #
-      # @todo support search field formatting?
       # @param type [Symbol]
       # @param term [Hash] components and information as a hash
-      # @return [String]
+      # @return [String, nil]
       def format_term(type:, term:)
         return unless type.in? %i[facet display]
 
         # attempt to handle poorly coded record
         normalize_single_subfield(term[:parts].first) if term[:count] == 1 && term[:parts].first.present?
 
-        case type
-        when :facet
-          trim_trailing(:period, term[:parts].join('--').strip)
-        when :display
-          display_value = "#{term[:parts].join('--')} #{term[:append].join(' ')}".strip
-          display_value.ends_with?('.') ? display_value : "#{display_value}."
-        end
+        value = case type
+                when :facet
+                  trim_trailing(:period, term[:parts].join('--').strip)
+                when :display
+                  display_value = "#{term[:parts].join('--')} #{term[:append].join(' ')}".strip
+                  display_value.ends_with?('.') ? display_value : "#{display_value}."
+                end
+
+        term[:override] ? HeadingControl.term_override(value) : value
       end
 
       # Is a field intended for display in a general subject field? To be included, the field tag is in either
@@ -251,13 +246,14 @@ module PennMARC
       #       heading. - MG
       # @todo do i need all this?
       # @param field [MARC::DataField]
+      # @param override [Boolean]
       # @return [Hash{Symbol => Integer, Array, Boolean, String}, Nil]
-      def build_subject_hash(field)
+      def build_subject_hash(field, override)
         term_info = { count: 0, parts: [], append: [], uri: nil,
                       local: field.indicator2 == '4' || field.tag.starts_with?('69'), # local subject heading
                       vernacular: field.tag == '880',
-                      subfield_a: nil,
-                      lcsh: lcsh?(field) }
+                      override: override && HeadingControl.overrideable_field?(field),
+                      subfield_a: nil, lcsh: lcsh?(field) }
         field.each do |subfield|
           case subfield.code
           when '0', '6', '8', '5', '7'

data/lib/pennmarc/helpers/title.rb

@@ -68,7 +68,7 @@ module PennMARC
         record.fields(%w[245 880]).filter_map { |field|
           next if field.tag == '880' && no_subfield_value_matches?(field, '6', /^245/)
 
-          join_subfields(field, &subfield_not_in?(%w[c 6 8 h]))
+          join_subfields(field, &subfield_not_in?(%w[c 6 7 8 h]))
         }.uniq
       end
 
@@ -77,7 +77,7 @@ module PennMARC
       # @param record [MARC::Record]
       # @return [Array<String>] array of auxiliary title values for search
       def search_aux(record)
-        values = search_aux_values(record: record, title_type: :main, &subfield_not_in?(%w[c 6 8])) +
+        values = search_aux_values(record: record, title_type: :main, &subfield_not_in?(%w[c 6 7 8])) +
                  search_aux_values(record: record, title_type: :related, &subfield_in?(%w[s t])) +
                  search_aux_values(record: record, title_type: :entity, &subfield_in?(%w[t])) +
                  search_aux_values(record: record, title_type: :note, &subfield_in?(%w[t]))
@@ -95,7 +95,7 @@ module PennMARC
         record.fields(%w[245 880]).filter_map { |field|
           next if field.tag == '880' && no_subfield_value_matches?(field, '6', /^245/)
 
-          join_subfields(field, &subfield_not_in?(%w[c 6 8 h]))
+          join_subfields(field, &subfield_not_in?(%w[c 6 7 8 h]))
         }.uniq
       end
 
@@ -105,7 +105,7 @@ module PennMARC
       # @param record [MARC::Record]
       # @return [Array<String>] auxiliary journal title information for search
       def journal_search_aux(record)
-        values = search_aux_values(record: record, title_type: :main, journal: true, &subfield_not_in?(%w[c 6 8])) +
+        values = search_aux_values(record: record, title_type: :main, journal: true, &subfield_not_in?(%w[c 6 7 8])) +
                  search_aux_values(record: record, title_type: :related, journal: true, &subfield_in?(%w[s t])) +
                  search_aux_values(record: record, title_type: :entity, journal: true, &subfield_in?(%w[t])) +
                  search_aux_values(record: record, title_type: :note, journal: true, &subfield_in?(%w[t]))
@@ -120,20 +120,20 @@ module PennMARC
       # @return [String] single title for display
       def show(record)
         field = record.fields('245')&.first
-        return Array.wrap(NO_TITLE_PROVIDED) unless field.present?
+        return NO_TITLE_PROVIDED unless field.present?
 
         values = title_values(field)
         [format_title(values[:title_or_form]), values[:punctuation], values[:other_info]].compact_blank.join(' ')
       end
 
-      # Same as show, but with all subfields included as found - except for subfield c.
+      # Same as show, but with most subfields included as found.
       # @param record [MARC::Record]
       # @return [String] detailed title for display
       def detailed_show(record)
         field = record.fields('245')&.first
         return unless field
 
-        join_subfields(field, &subfield_not_in?(%w[6 8]))
+        join_subfields(field, &subfield_not_in?(%w[6 7 8]))
       end
 
       # Same structure as show, but linked alternate title.
@@ -198,7 +198,7 @@ module PennMARC
       # @return [Array<String>] Array of standardized titles as strings
       def standardized_show(record)
         standardized_titles = record.fields(%w[130 240]).map do |field|
-          join_subfields(field, &subfield_not_in?(%w[0 6 8 e w]))
+          join_subfields(field, &subfield_not_in?(%w[0 6 7 8 e w]))
         end
         standardized_titles += record.fields('730').filter_map do |field|
           # skip unless one of the indicators is blank
@@ -207,13 +207,13 @@ module PennMARC
           # skip if a subfield i is present
           next if subfield_defined?(field, 'i')
 
-          join_subfields(field, &subfield_not_in?(%w[5 6 8 e w]))
+          join_subfields(field, &subfield_not_in?(%w[5 6 7 8 e w]))
         end
         titles = standardized_titles + record.fields('880').filter_map do |field|
           next unless subfield_undefined?(field, 'i') &&
                       subfield_value?(field, '6', /^(130|240|730)/)
 
-          join_subfields field, &subfield_not_in?(%w[5 6 8 e w])
+          join_subfields field, &subfield_not_in?(%w[5 6 7 8 e w])
         end
         titles.uniq
       end
@@ -227,18 +227,18 @@ module PennMARC
       # @return [Array<String>] Array of other titles as strings
       def other_show(record)
         other_titles = record.fields('246').map do |field|
-          join_subfields(field, &subfield_not_in?(%w[6 8]))
+          join_subfields(field, &subfield_not_in?(%w[6 7 8]))
         end
         other_titles += record.fields('740')
                               .filter_map do |field|
                                 next unless field.indicator2.in? ['', ' ', '0', '1', '3']
 
-                                join_subfields(field, &subfield_not_in?(%w[5 6 8]))
+                                join_subfields(field, &subfield_not_in?(%w[5 6 7 8]))
         end
         titles = other_titles + record.fields('880').filter_map do |field|
           next unless subfield_value? field, '6', /^(246|740)/
 
-          join_subfields(field, &subfield_not_in?(%w[5 6 8]))
+          join_subfields(field, &subfield_not_in?(%w[5 6 7 8]))
         end
         titles.uniq
       end
@@ -257,7 +257,7 @@ module PennMARC
                 next unless field.tag == '247' || (field.tag == '880' && subfield_value?(field, '6', /^247/))
 
                 # 6 and 8 are not meaningful for display
-                former_title = join_subfields field, &subfield_not_in?(%w[6 8 e w])
+                former_title = join_subfields field, &subfield_not_in?(%w[6 7 8 e w])
                 former_title_append = join_subfields field, &subfield_in?(%w[e w])
                 "#{former_title} #{former_title_append}".strip
               }.uniq

data/lib/pennmarc/mappings/headings_override.yml

@@ -3,10 +3,21 @@
 # read "Illegal Noncitizens".
 # Also, use lower case only in the key to support efficient case-insensitive matching.
 "illegal alien children": Undocumented immigrant children
-"alien detention centers": Immigrant detention centers
+"alien detention centers": Noncitizen detention centers
 "alien criminals": Noncitizen criminals
-"alien property": Foreign-owned property
+"alien property": Foreign property
 "illegal aliens": Undocumented immigrants
 "alien labor": Foreign workers
 gypsies: Romanies
 aliens: Noncitizens
+"east indian americans": Indian Americans
+"east indian american": Indian American
+"east indians": Indians (India)
+"east indian": Indian (India)
+"indians of north america": Indigenous peoples of North America
+"indians of south america": Indigenous peoples of South America
+"indians of central america": Indigenous peoples of Central America
+"indians of mexico": Indigenous peoples of Mexico
+"indians of the west indies": Indigenous peoples of the West Indies
+"memphis race riot, memphis, tenn., 1866": Memphis Race Massacre, Memphis, Tenn., 1866
+"east saint louis race riot, east saint louis, ill., 1917": East Saint Louis Race Massacre, East Saint Louis, Ill., 1917

data/lib/pennmarc/mappings/locations.yml

@@ -856,6 +856,10 @@ muselock:
     - Penn Museum Library
   display: Penn Museum Library - Locked Cases (ask staff)
   aeon: true
+musemap:
+  specific_location: Penn Museum Library - Maps
+  library: Penn Museum Library
+  display: Penn Museum Library - Maps
 musemedia:
   specific_location: Penn Museum Library - Media
   library: Penn Museum Library

data/lib/pennmarc/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PennMARC
-  VERSION = '1.4.9'
+  VERSION = '1.4.12'
 end

data/spec/lib/pennmarc/heading_control_spec.rb

@@ -8,45 +8,35 @@ describe 'PennMARC::HeadingControl' do
   describe '.process' do
     context 'with a term for removal' do
       it 'removes the term if found in isolation' do
-        values = [remove_term]
-        expect(PennMARC::HeadingControl.term_override(values)).to eq []
+        expect(PennMARC::HeadingControl.term_override(remove_term)).to be_nil
       end
 
       it 'removes the term regardless of case' do
-        values = [remove_term.downcase]
-        expect(PennMARC::HeadingControl.term_override(values)).to eq []
+        expect(PennMARC::HeadingControl.term_override(remove_term.downcase)).to be_nil
       end
 
       it 'removes the term if it is included as a substring' do
-        values = ["#{remove_term}--History"]
-        expect(PennMARC::HeadingControl.term_override(values)).to eq []
+        value = "#{remove_term}--History"
+        expect(PennMARC::HeadingControl.term_override(value)).to be_nil
       end
     end
 
     PennMARC::Mappers.heading_overrides.each do |target, replacement|
       context "with the \"#{target}\" term" do
         it 'replaces the term in isolation' do
-          values = [target]
-          expect(PennMARC::HeadingControl.term_override(values)).to eq [replacement]
+          expect(PennMARC::HeadingControl.term_override(target)).to eq replacement
         end
 
         it 'replaces the term when used with other headings' do
-          values = ["#{target}--History"]
-          expect(PennMARC::HeadingControl.term_override(values)).to eq ["#{replacement}--History"]
+          value = "#{target}--History"
+          expect(PennMARC::HeadingControl.term_override(value)).to eq "#{replacement}--History"
         end
 
         it 'replaces the term regardless of case' do
-          values = ["#{target.titleize}--History"]
-          expect(PennMARC::HeadingControl.term_override(values)).to eq ["#{replacement}--History"]
+          value = "#{target.titleize}--History"
+          expect(PennMARC::HeadingControl.term_override(value)).to eq "#{replacement}--History"
         end
       end
     end
-
-    context 'with a variety of terms' do
-      it 'removes and replaces terms as needed' do
-        values = [remove_term, replace_term, 'History']
-        expect(PennMARC::HeadingControl.term_override(values)).to contain_exactly 'History', replaced_term
-      end
-    end
   end
 end

data/spec/lib/pennmarc/helpers/creator_spec.rb

@@ -192,6 +192,23 @@ describe 'PennMARC::Creator' do
                                           'Name ends with comma', 'Name with no comma'
       end
     end
+
+    context 'with university donor/fund provenance' do
+      let(:fields) do
+        [marc_field(tag: '100', subfields: { a: 'Surname, Name', '0': 'http://cool.uri/12345', d: '1900-2000',
+                                             e: 'author.', '4': 'http://cool.uri/vocabulary/relators/aut' }),
+         marc_field(tag: '700', subfields: { a: 'A contributor', e: 'contributor',
+                                             '5': "Does-not-start-with-#{helper::UNIVERSITY_IDENTIFIER}" }),
+         marc_field(tag: '700', subfields: { a: 'Important Person Collection', '6': '100', d: '1970-',
+                                             '5': helper::UNIVERSITY_IDENTIFIER }),
+         marc_field(tag: '710', subfields: { a: 'Important Person Collection Library', '6': '100', d: '1970-',
+                                             '5': helper::UNIVERSITY_IDENTIFIER })]
+      end
+
+      it 'omits any university donor/fund provenance' do
+        expect(helper.authors_list(record)).to contain_exactly 'Surname, Name', 'A contributor'
+      end
+    end
   end
 
   describe '.contributors_list' do
@@ -245,6 +262,21 @@ describe 'PennMARC::Creator' do
                                           ['Translator', ['Einstein, Albert 1970-, Translator']]
       end
     end
+
+    context 'with university donor/fund provenance' do
+      let(:fields) do
+        [marc_field(tag: '700', subfields: { a: 'Surname, Name', '0': 'http://cool.uri/12345', d: '1900-2000',
+                                             e: 'author.', '4': 'http://cool.uri/vocabulary/relators/aut' }),
+         marc_field(tag: '700', subfields: { a: 'Important Person Collection', '6': '100', d: '1970-',
+                                             '5': helper::UNIVERSITY_IDENTIFIER }),
+         marc_field(tag: '710', subfields: { a: 'Important Person Collection Library', '6': '100', d: '1970-',
+                                             '5': helper::UNIVERSITY_IDENTIFIER })]
+      end
+
+      it 'omits any university donor/fund provenance' do
+        expect(helper.contributors_list(record)).to contain_exactly ['Author', ['Surname, Name']]
+      end
+    end
   end
 
   describe '.show_facet_map' do

data/spec/lib/pennmarc/helpers/subject_spec.rb

@@ -199,6 +199,20 @@ describe 'PennMARC::Subject' do
                                           'Franklin, Benjamin', 'Philadelphia (Pa.)')
       end
     end
+
+    context 'with a record with fields not subject to overriding' do
+      let(:replace_term) { PennMARC::Mappers.heading_overrides.keys[2] }
+      let(:fields) do
+        [marc_field(tag: '650', indicator2: '0', subfields: { a: replace_term }),
+         marc_field(tag: PennMARC::HeadingControl::NO_OVERRIDE_TAGS.sample, indicator2: '0',
+                    subfields: { a: replace_term })]
+      end
+
+      it 'only overrides in the allowed field' do
+        replaced_term = PennMARC::HeadingControl.term_override(replace_term)
+        expect(values).to contain_exactly(replace_term, replaced_term)
+      end
+    end
   end
 
   describe '.show' do

data/spec/lib/pennmarc/helpers/title_spec.rb

@@ -142,7 +142,7 @@ describe 'PennMARC::Title' do
       end
 
       it 'returns default title' do
-        expect(helper.show(record)).to eq [PennMARC::Title::NO_TITLE_PROVIDED]
+        expect(helper.show(record)).to eq PennMARC::Title::NO_TITLE_PROVIDED
       end
     end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pennmarc
 version: !ruby/object:Gem::Version
-  version: 1.4.9
+  version: 1.4.12
 platform: ruby
 authors:
 - Mike Kanning
@@ -12,7 +12,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-09-21 00:00:00.000000000 Z
+date: 2026-11-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -94,8 +94,8 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".gitlab-ci.yml"
+- ".gitlab/ci-requirements.yml"
 - ".gitleaks.toml"
-- ".pipeline.yml"
 - ".rspec"
 - ".rubocop.yml"
 - ".rubocop_todo.yml"

data/.pipeline.yml

@@ -1,73 +0,0 @@
-variables:
-  FF_SCRIPT_SECTIONS: "true"
-  GIT_CLONE_PATH: "${CI_BUILDS_DIR}/${CI_PROJECT_NAME}/${CI_JOB_ID}"
-
-include:
-  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/install_hashicorp_vault@~latest
-  - component: gitlab.library.upenn.edu/devops/gitlab/components/general/vault_jwt_auth@~latest
-    inputs:
-        vault_addr: ${VAULT_ADDR}
-        vault_auth_path: ${VAULT_AUTH_PATH}
-        vault_auth_role: ${VAULT_AUTH_ROLE}
-
-  - project: "devops/gitlab/ci-templates/ruby"
-    ref: "sans-dind"
-    file:
-      - ".rspec.yml"
-      - ".rubocop.yml"
-
-stages:
-  - test
-  - deploy
-
-rspec_app_test:
-  stage: test
-  image: ruby:3.2.2
-  before_script:
-    - bundle install -j $(nproc)
-  extends:
-    - .rspec
-  tags:
-    - build
-
-rubocop_app_test:
-  stage: test
-  image: ruby:3.2.2
-  before_script:
-    - bundle install -j $(nproc)
-  extends:
-    - .rubocop
-  tags:
-    - build
-
-# This step was inspired from Gitlab's example of gem publication:
-# https://gitlab.com/gitlab-org/quality/pipeline-common/-/blob/master/ci/gem-release.yml
-gem_publication:
-  stage: deploy
-  image: ruby:3.2.2
-  extends:
-    - .vault_jwt_auth
-  variables:
-    GEMSPEC_FILE: "${CI_PROJECT_NAME}.gemspec"
-  before_script:
-    - !reference [.install_hashicorp_vault, before_script]
-    - !reference [.vault_jwt_auth, before_script]
-  script:
-    - export GEM_HOST_API_KEY="$(vault kv get -field=rubygems_api_key ${VAULT_KV_ENDPOINT}${ENVIRONMENT})"
-    - |
-      gem -v
-      rm -f ./*.gem
-      [ -f "${GEMSPEC_FILE}" ] || (echo "No ${GEMSPEC_FILE} file found!" && exit 1)
-    - '[ -n "${GEM_HOST_API_KEY}" ] || (echo "GEM_HOST_API_KEY is not set!" && exit 1)'
-    - GEM_FILE=$(echo "${CI_PROJECT_NAME}-${CI_COMMIT_TAG:1}.gem")
-    - |
-      gem build "${GEMSPEC_FILE}"
-      [ -f "${GEM_FILE}" ] || (echo "No ${GEM_FILE} file found!" && exit 1)
-    - '[ "${DISABLE_GEM_PUSH}" == "true" ] || gem push "${GEM_FILE}"'
-  rules:
-     - if: $CI_COMMIT_TAG =~ /^v\d+\.\d+\.\d+(\.[a-zA-Z0-9]+)?$/
-  artifacts:
-    paths:
-      - "*.gem"
-  tags:
-    - deploy