pennmarc 1.0.2 → 1.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 33527bf43532170690b9b591097fb03f854130b3383debfafe931417d0394f52
-  data.tar.gz: a18a5be08df6d7b74d2aaa61275cdecdedec6caa4b5e8b2b81c99e91411ce093
+  metadata.gz: 50fd0383f0e78807f62f8abe784f75d8dace6e5b0ecf64877f79ad90b6d40354
+  data.tar.gz: 3df19d10534fc787c55814e30bd1b066a8c5ea10e7da15f9b320c4500891e0be
 SHA512:
-  metadata.gz: 627a4da06351037f520bc02b0a9fd61ce6cfdec35c563f2b29e3c1c01b4ad76766f155630cafe680b010783ea4f4c285df2d499fd784b7ee4f3cb4948cd421dd
-  data.tar.gz: c966233bb00009a14babc5bc92f0399e75640e886f7c32d176fea8983813aca8936d0e8fab98576a797afaf0b60c5f24268c2ae4e2d8cca31900e590db0a9bc6
+  metadata.gz: 277bb7c15e224c8134b8cea8b28de474d27022a1537904844af8c5542ff3f0080c37f13db38a5a9463a07453bcc403ccf346c2b5538c2fe26012df6a67dec24f
+  data.tar.gz: 1ca8e643758f86aeabdfbeb1576f513c866ba5ef1a40b6edaa279f687af7644baf6b953db6f078548fc72ca99b75b6377db7d80d98a19059c797b6ad41b5f648

data/.gitleaks.toml

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

data/README.md

@@ -73,7 +73,7 @@ rspec
 
 1. Update the version in `pennmarc.gemspec`
 2. Run `gem build pennmarc.gemspec` with the latest code
-3. Run `gem push pennmarc-{version number here}`(e.g. `gem push pennmarc-1.0.0`) to push to RubyGems. You will need access and MFA setup with RubyGems.
+3. Run `gem push pennmarc-{version number here}.gem`(e.g. `gem push pennmarc-1.0.0.gem`) to push to RubyGems. You will need access and MFA setup with RubyGems.
 
 ## QA
 
@@ -89,4 +89,4 @@ MARC_FILE=path/to/marc.xml bundle exec rake pennmarc:parse
  - rake task or some similar command to return a full set of values extracted from a specified marcxml file
  - Pipeline to run tests and publish to Rubygems
     - rubocop check
-    - rdoc/yard coverage checks?
+    - rdoc/yard coverage checks?

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/format.rb

@@ -41,10 +41,10 @@ module PennMARC
         results += record.fields('880').map do |f|
           subfield_to_ignore = if subfield_value?(f, 6, /^300/)
                                  %w[3 6 8]
-                               elsif subfield_value?(f, 6, /^(254|255|310|342|352|362)/)
-                                 %w[6 8]
                                elsif subfield_value?(f, 6, /^340/)
                                  %w[0 2 6 8]
+                               else
+                                 %w[6 8]
                                end
           join_subfields(f, &subfield_not_in?(subfield_to_ignore))
         end

data/lib/pennmarc/helpers/identifier.rb

@@ -23,7 +23,7 @@ module PennMARC
           if field.tag == '020'
             field.filter_map { |subfield| normalize_isbn(subfield.value) if subfield_in?(%w[a z]).call(subfield) }
           else
-            field.filter_map { |subfield| subfield.value if subfield_in?(%w[a l z]).call(subfield) }
+            field.filter_map { |subfield| subfield.value if subfield_in?(%w[a l m y z]).call(subfield) }
           end
         }.flatten.uniq
       end
@@ -56,21 +56,42 @@ module PennMARC
 
       # Get numeric OCLC ID of first {https://www.oclc.org/bibformats/en/0xx/035.html 035 field}
       # with an OCLC ID defined in subfield 'a'.
-      #
-      # @todo We should evaluate this to return a single value in the future since subfield a is non-repeatable
       # @param [MARC::Record] record
-      # @return [Array<String>]
-      def oclc_id(record)
-        oclc_id = Array.wrap(record.fields('035')
-                         .find { |field| field.any? { |subfield| subfield_a_is_oclc?(subfield) } })
-
-        oclc_id.flat_map do |field|
+      # @return [String, nil]
+      def oclc_id_show(record)
+        ids = Array.wrap(record.fields('035')
+                           .find { |field| field.any? { |subfield| subfield_a_is_oclc?(subfield) } })
+        ids.flat_map { |field|
           field.filter_map do |subfield|
             # skip unless subfield 'a' is an oclc id value
             next unless subfield_a_is_oclc?(subfield)
 
             # search for numeric part of oclc id (e.g. '610094484' in '(OCoLC)ocn610094484')
-            match = /^\s*\(OCoLC\)[^1-9]*([1-9][0-9]*).*$/.match(subfield.value)
+            match = match_oclc_number(subfield)
+
+            # skip unless search to find numeric part of oclc id has a match
+            next unless match
+
+            match[1]
+          end
+        }.first
+      end
+
+      # Retrieve valid and invalid numeric OCLC IDs from {https://www.oclc.org/bibformats/en/0xx/035.html 035 field}
+      # for search.
+      # @param [MARC::Record] record
+      # @return [Array<String>]
+      def oclc_id_search(record)
+        record.fields('035').flat_map do |field|
+          field.filter_map do |subfield|
+            # skip unless subfield 'a' or 'z'
+            next unless subfield.code.in?(%w[a z])
+
+            # skip unless subfield value matches OCLC ID
+            next unless subfield_is_oclc?(subfield)
+
+            # search for numeric part of oclc id
+            match = match_oclc_number(subfield)
 
             # skip unless search to find numeric part of oclc id has a match
             next unless match
@@ -143,7 +164,19 @@ module PennMARC
       # @param [MARC::Subfield]
       # @return [TrueClass, FalseClass]
       def subfield_a_is_oclc?(subfield)
-        subfield.code == 'a' && (subfield.value =~ /^\(OCoLC\).*/).present?
+        subfield.code == 'a' && subfield_is_oclc?(subfield)
+      end
+
+      # @param [MARC::Subfield]
+      # @return [TrueClass, FalseClass]
+      def subfield_is_oclc?(subfield)
+        (subfield.value =~ /^\(OCoLC\).*/).present?
+      end
+
+      # @param [MARC::Subfield]
+      # @return [MatchData, nil]
+      def match_oclc_number(subfield)
+        /^\s*\(OCoLC\)[^1-9]*([1-9][0-9]*).*$/.match(subfield.value)
       end
 
       # Normalize isbn value using {https://github.com/billdueber/library_stdnums library_stdnums gem}.

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]