pennmarc 1.0.3 → 1.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 28dc70104803899434767b340182cb8eecff8c402cfb5e8547058d560a45a1e5
-  data.tar.gz: 1fc0897f12ffb24de8bc0f40b69474d29264c036e33ba4ea97390b60a9f60c43
+  metadata.gz: 9aa7e5cf7ade86fc51db4d35791eed5e3e38784e35d33bd9b82379a91ab3786e
+  data.tar.gz: 8b2668fbfd1fc645b203e23f12cfe5681014a870fa504f45c7c0b034682be325
 SHA512:
-  metadata.gz: c82d8a22f480a768a8f6cce3cb7bc2ed25f7d5b202e3b492ac572a6f5bfec0d801098e1d74db8eb470573a2afbdd9314a90e18955a576c9ff5dee42aa2fbc5cd
-  data.tar.gz: d3c69ce76e13c50b0f2da649ea9499dcb93a734944d298cb783e71e0c4bc59c76fad0ea344353124f024524d11b5f8c92318771d780848506d50940f483c427b
+  metadata.gz: aff6902488cb0d85bee32f3a3c5f4b613c8c5867ab3b594af40dad4c54e501b735b79fbed1ba8656c1144b87b58a9edc6e0ed961cc62603c7ccefb0c244b3117
+  data.tar.gz: e262a56ed0512de8c93c4ef0f94f87c322904d44ed845a64b9eb8dc58c8c3cc9c62675d52e314c5cd15eba0d7f4daea4725675af0c3e96ac7cb501a55074edf7

data/.gitleaks.toml

@@ -0,0 +1,2 @@
+[file]
+paths-exclude = ["lib/pennmarc/mappings/language.yml"]

data/.rubocop_todo.yml

@@ -1,36 +1,12 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config --auto-gen-only-exclude --exclude-limit 10000`
-# on 2023-08-25 13:55:25 UTC using RuboCop version 1.51.0.
+# on 2023-11-08 20:19:45 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
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, IndentationWidth.
-# SupportedStyles: with_first_argument, with_fixed_indentation
-Layout/ArgumentAlignment:
-  Exclude:
-    - 'spec/lib/pennmarc/helpers/series_spec.rb'
-
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: empty_lines, no_empty_lines
-Layout/EmptyLinesAroundBlockBody:
-  Exclude:
-    - 'spec/lib/pennmarc/helpers/identifer_spec.rb'
-
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: final_newline, final_blank_line
-Layout/TrailingEmptyLines:
-  Exclude:
-    - 'spec/lib/pennmarc/helpers/identifer_spec.rb'
-
-# Offense count: 22
+# Offense count: 23
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
@@ -38,6 +14,7 @@ Metrics/AbcSize:
     - 'lib/pennmarc/helpers/edition.rb'
     - 'lib/pennmarc/helpers/format.rb'
     - 'lib/pennmarc/helpers/genre.rb'
+    - 'lib/pennmarc/helpers/language.rb'
     - 'lib/pennmarc/helpers/location.rb'
     - 'lib/pennmarc/helpers/note.rb'
     - 'lib/pennmarc/helpers/production.rb'
@@ -66,6 +43,7 @@ Metrics/CyclomaticComplexity:
     - 'lib/pennmarc/helpers/edition.rb'
     - 'lib/pennmarc/helpers/format.rb'
     - 'lib/pennmarc/helpers/genre.rb'
+    - 'lib/pennmarc/helpers/language.rb'
     - 'lib/pennmarc/helpers/note.rb'
     - 'lib/pennmarc/helpers/production.rb'
     - 'lib/pennmarc/helpers/relation.rb'
@@ -104,6 +82,7 @@ Metrics/PerceivedComplexity:
     - 'lib/pennmarc/helpers/edition.rb'
     - 'lib/pennmarc/helpers/format.rb'
     - 'lib/pennmarc/helpers/genre.rb'
+    - 'lib/pennmarc/helpers/language.rb'
     - 'lib/pennmarc/helpers/note.rb'
     - 'lib/pennmarc/helpers/production.rb'
     - 'lib/pennmarc/helpers/series.rb'
@@ -152,16 +131,9 @@ RSpec/FilePath:
   Exclude:
     - 'spec/lib/pennmarc/parser_spec.rb'
 
-# Offense count: 4
+# Offense count: 6
 # Configuration parameters: Max, AllowedGroups.
 RSpec/NestedGroups:
   Exclude:
+    - 'spec/lib/pennmarc/helpers/access_spec.rb'
     - 'spec/lib/pennmarc/helpers/format_spec.rb'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Max, AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, AllowedPatterns.
-# URISchemes: http, https
-Layout/LineLength:
-  Exclude:
-    - 'spec/lib/pennmarc/helpers/creator_spec.rb'

data/lib/pennmarc/helpers/access.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Methods for extracting how a record can be accessed
+  class Access < Helper
+    ONLINE = 'Online'
+    AT_THE_LIBRARY = 'At the library'
+
+    class << self
+      # Based primarily on the "enhanced MARC" fields added by Alma, determine if the record has
+      # electronic access or has physical holding, and is therefore "Online" or "At the library". If a record is "At the
+      # library", but has a link to a finding aid in the 856 field (matching certain criteria), also add 'Online' as an
+      # access method.
+      # @todo What if none of these criteria match? Should we include "At the library" by default? Records with no value
+      #       in this field would be lost if the user selects a facet value.
+      # @param [MARC::Record] record
+      # @return [Array]
+      def facet(record)
+        acc = record.filter_map do |field|
+          next AT_THE_LIBRARY if field.tag == EnrichedMarc::TAG_HOLDING
+          next ONLINE if field.tag == EnrichedMarc::TAG_ELECTRONIC_INVENTORY
+        end
+
+        return acc if acc.size == 2 # return early if all values are already present
+
+        acc << ONLINE if acc.exclude?(ONLINE) && finding_aid_linkage?(record) # only check if ONLINE isn't already there
+        acc
+      end
+
+      private
+
+      # Check if a record contains an 856 entry for an online finding aid, meeting these criteria:
+      # 1. Indicator 1 is 4 (HTTP resource)
+      # 2. Indicator 2 is NOT 2 (indicating the linkage is to a "related" thing)
+      # 3. The URL specified in subfield u (URI) is a Penn Handle link
+      # See: https://www.loc.gov/marc/bibliographic/bd856.html
+      # @param [MARC::Record] record
+      # @return [Boolean]
+      def finding_aid_linkage?(record)
+        record.fields('856').filter_map do |field|
+          next if field.indicator2 == '2' || field.indicator1 != '4'
+
+          subz = subfield_values(field, 'z')
+          subfield_values(field, 'u').filter_map do |value|
+            return true if subz.include?('Finding aid') && value.include?('hdl.library.upenn.edu')
+          end
+        end
+        false
+      end
+    end
+  end
+end

data/lib/pennmarc/helpers/date.rb

@@ -25,21 +25,17 @@ module PennMARC
       # @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|
-          field.filter_map do |subfield|
-            # skip unless field has date created subfield
-            next unless subfield_defined?(field, EnrichedMarc::SUB_ITEM_DATE_CREATED)
-
+          subfield_values(field, EnrichedMarc::SUB_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
             # foreseeable future we should support both formats.
 
-            format = subfield.value.size == 10 ? '%Y-%m-%d' : '%Y-%m-%d %H:%M:%S'
-
-            DateTime.strptime(subfield.value, format)
+            format = date_added.size == 10 ? '%Y-%m-%d' : '%Y-%m-%d %H:%M:%S'
 
+            DateTime.strptime(date_added, format)
           rescue StandardError => e
-            puts "Error parsing date in date added subfield: #{subfield.value} - #{e}"
+            puts "Error parsing date in date added subfield: #{date_added} - #{e}"
             nil
           end
         }.max

data/lib/pennmarc/helpers/language.rb

@@ -4,10 +4,10 @@ module PennMARC
   # Logic for extracting and translating Language values for a record. Penn practice is to verify the value present in
   # the {https://www.oclc.org/bibformats/en/fixedfield/lang.html 008 control field} as a three letter code. This code
   # is then mapped to a display-friendly value using the a provided mapping hash.
-  # @todo should we consider values in the {https://www.oclc.org/bibformats/en/0xx/041.html 041 field}?
   class Language < Helper
     # Used when no value is present in the control field - still mapped
     UNDETERMINED_CODE = :und
+    LANGUAGE_SUBFIELDS = %w[a b d e g h i j k m n p q r t].freeze
 
     class << self
       # Get language values for display from the {https://www.oclc.org/bibformats/en/5xx/546.html 546 field} and
@@ -21,16 +21,31 @@ module PennMARC
         values + linked_alternate(record, '546', &subfield_not_in?(%w[6 8]))
       end
 
-      # Get language values for searching and faceting of a record. The value is extracted from a defined position in
-      # the 008 control field. Language facet and search values will typically be the same.
+      # Get language values for searching and faceting of a record. The values are extracted from subfields
+      # in the 041 field. Language facet and search values will typically be the same, with the exception of `zxx`,
+      # when no linguistic content is found.
+      #
+      # @note In franklin, we extracted the language code from the 008 control field. After engaging cataloging unit
+      #   representatives, we decided to extract these values from the 041 field: Includes records for multilingual
+      #   items, items that involve translation, and items where the medium of communication is a sign language.
+      #   https://www.loc.gov/marc/bibliographic/bd041.html
       #
       # @param [MARC::Record] record
-      # @param [Hash] language_map hash for language code translation
-      # @return [String] nice value for language
-      def search(record, language_map: Mappers.language)
+      # @param [Hash] iso_639_2_mapping iso-639-2 spec hash for language code translation
+      # @param [Hash] iso_639_3_mapping iso-639-3 spec hash for language code translation
+      # @return [Array] array of language values
+      def values(record, iso_639_2_mapping: Mappers.iso_639_2_language, iso_639_3_mapping: Mappers.iso_639_3_language)
+        values = record.fields('041').filter_map { |field|
+          mapper = subfield_value?(field, '2', /iso639-3/) ? iso_639_3_mapping : iso_639_2_mapping
+          field.filter_map do |sf|
+            next unless LANGUAGE_SUBFIELDS.include? sf.code
+
+            mapper[sf.value&.to_sym]
+          end
+        }.flatten
         control_field = record['008']&.value
-        language_code = control_field[35..37]
-        language_map[language_code.to_sym || UNDETERMINED_CODE]
+        values << iso_639_2_mapping[control_field[35..37]&.to_sym] if control_field.present?
+        values.empty? ? values << iso_639_2_mapping[UNDETERMINED_CODE] : values.uniq
       end
     end
   end

data/lib/pennmarc/mappers.rb

@@ -5,8 +5,12 @@ module PennMARC
   class Mappers
     class << self
       # @return [Hash]
-      def language
-        @language ||= load_map('language.yml')
+      def iso_639_2_language
+        @iso_639_2_language ||= load_map('iso639-2-languages.yml')
+      end
+
+      def iso_639_3_language
+        @iso_639_3_language ||= load_map('iso639-3-languages.yml')
       end
 
       # @return [Hash]