pennmarc 0.0.1

data/legacy/test_file_output.json

@@ -0,0 +1,49 @@
+{ "id":["FRANKLIN_9910148543503681"],
+  "grouped_id":["18521155!FRANKLIN_9910148543503681"],
+  "record_source_id":[1],
+  "record_source_f":["Penn"],
+  "nocirc_f_stored":["none"],
+  "alma_mms_id":["9910148543503681"],
+  "oclc_id":["18521155"],
+  "cluster_id":["18521155"],
+  "marcrecord_xml_stored_single_large":["<record><leader>01908cam a2200469 a 4500</leader><controlfield tag=\"005\">20220609191957.0</controlfield><controlfield tag=\"008\">890224t19891989nyua          001 0 eng  </controlfield><controlfield tag=\"001\">9910148543503681</controlfield><datafield tag=\"010\" ind1=\" \" ind2=\" \"><subfield code=\"a\">   88029825 </subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">(OCoLC)ocm18521155</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">(OCoLC)18521155</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">(CStRLIN)PAUG89-B7246</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">(CaOTULAS)185188489</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"9\">AHA6856</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">1014854</subfield></datafield><datafield tag=\"035\" ind1=\" \" ind2=\" \"><subfield code=\"a\">(PU)1014854-penndb-Voyager</subfield></datafield><datafield tag=\"040\" ind1=\" \" ind2=\" \"><subfield code=\"b\">eng</subfield><subfield code=\"d\">CSt-B</subfield></datafield><datafield tag=\"043\" ind1=\" \" ind2=\" \"><subfield code=\"a\">n-us---</subfield></datafield><datafield tag=\"050\" ind1=\"0\" ind2=\" \"><subfield code=\"a\">KF6450</subfield><subfield code=\"b\">.C59 1989</subfield></datafield><datafield tag=\"082\" ind1=\"0\" ind2=\" \"><subfield code=\"a\">343.7306/8</subfield><subfield code=\"a\">347.30368</subfield><subfield code=\"2\">19</subfield></datafield><datafield tag=\"090\" ind1=\" \" ind2=\" \"><subfield code=\"a\">KF6450</subfield><subfield code=\"b\">.C59 1989</subfield><subfield code=\"i\">11/30/89 CTZ</subfield></datafield><datafield tag=\"245\" ind1=\"0\" ind2=\"4\"><subfield code=\"a\">The Coopers &amp; Lybrand guide to business tax strategies and planning /</subfield><subfield code=\"c\">by the partners of Coopers &amp; Lybrand.</subfield></datafield><datafield tag=\"264\" ind1=\" \" ind2=\"1\"><subfield code=\"a\">New York :</subfield><subfield code=\"b\">Simon and Schuster,</subfield><subfield code=\"c\">[1989]</subfield></datafield><datafield tag=\"264\" ind1=\" \" ind2=\"4\"><subfield code=\"c\">©1989</subfield></datafield><datafield tag=\"300\" ind1=\" \" ind2=\" \"><subfield code=\"a\">x, 198 pages :</subfield><subfield code=\"b\">illustrations ;</subfield><subfield code=\"c\">24 cm</subfield></datafield><datafield tag=\"336\" ind1=\" \" ind2=\" \"><subfield code=\"a\">text</subfield><subfield code=\"b\">txt</subfield><subfield code=\"2\">rdacontent</subfield></datafield><datafield tag=\"337\" ind1=\" \" ind2=\" \"><subfield code=\"a\">unmediated</subfield><subfield code=\"b\">n</subfield><subfield code=\"2\">rdamedia</subfield></datafield><datafield tag=\"338\" ind1=\" \" ind2=\" \"><subfield code=\"a\">volume</subfield><subfield code=\"b\">nc</subfield><subfield code=\"2\">rdacarrier</subfield></datafield><datafield tag=\"500\" ind1=\" \" ind2=\" \"><subfield code=\"a\">Edited by Jonathan J. Davies and others.</subfield></datafield><datafield tag=\"650\" ind1=\" \" ind2=\"0\"><subfield code=\"a\">Business enterprises</subfield><subfield code=\"x\">Taxation</subfield><subfield code=\"z\">United States.</subfield><subfield code=\"0\">http://id.loc.gov/authorities/subjects/sh2009118044</subfield></datafield><datafield tag=\"650\" ind1=\" \" ind2=\"7\"><subfield code=\"a\">Business enterprises</subfield><subfield code=\"x\">Taxation.</subfield><subfield code=\"2\">fast</subfield><subfield code=\"0\">http://id.worldcat.org/fast/842634</subfield></datafield><datafield tag=\"651\" ind1=\" \" ind2=\"7\"><subfield code=\"a\">United States.</subfield><subfield code=\"2\">fast</subfield><subfield code=\"0\">http://id.worldcat.org/fast/1204155</subfield></datafield><datafield tag=\"650\" ind1=\" \" ind2=\"0\"><subfield code=\"a\">Tax planning</subfield><subfield code=\"z\">United States.</subfield><subfield code=\"0\">http://id.loc.gov/authorities/subjects/sh2008112546</subfield></datafield><datafield tag=\"650\" ind1=\" \" ind2=\"7\"><subfield code=\"a\">Tax planning.</subfield><subfield code=\"2\">fast</subfield><subfield code=\"0\">http://id.worldcat.org/fast/1143815</subfield></datafield><datafield tag=\"700\" ind1=\"1\" ind2=\" \"><subfield code=\"a\">Davies, Jonathan J.</subfield><subfield code=\"0\">http://id.loc.gov/authorities/names/n82126416</subfield></datafield><datafield tag=\"710\" ind1=\"2\" ind2=\" \"><subfield code=\"a\">Coopers &amp; Lybrand.</subfield><subfield code=\"0\">http://id.loc.gov/authorities/names/n79063025</subfield></datafield><datafield tag=\"740\" ind1=\"0\" ind2=\" \"><subfield code=\"a\">Guide to business tax strategies and planning.</subfield></datafield><datafield tag=\"740\" ind1=\"0\" ind2=\" \"><subfield code=\"a\">Business tax strategies and planning</subfield></datafield><datafield tag=\"740\" ind1=\"0\" ind2=\" \"><subfield code=\"a\">Tax strategies and planning.</subfield></datafield><datafield tag=\"902\" ind1=\" \" ind2=\" \"><subfield code=\"a\">MARCIVE 2022</subfield></datafield><datafield tag=\"950\" ind1=\" \" ind2=\" \"><subfield code=\"l\">LIPP</subfield><subfield code=\"i\">11/30/89 C</subfield></datafield><datafield tag=\"955\" ind1=\" \" ind2=\" \"><subfield code=\"l\">LIPP</subfield><subfield code=\"c\">1</subfield><subfield code=\"q\">89-B7246-1</subfield><subfield code=\"r\">[01043 6272]</subfield><subfield code=\"i\">11/30/89 C</subfield></datafield></record>"],
+  "access_f_stored":["At the library"],
+  "format_f_stored":["Book"],
+  "author_creator_xfacet2_input":["nDavies, Jonathan J.","nCoopers & Lybrand"],
+  "subject_search":["Business enterprises Taxation United States. http://id.loc.gov/authorities/subjects/sh2009118044","Business enterprises Taxation. fast http://id.worldcat.org/fast/842634","United States. fast http://id.worldcat.org/fast/1204155","Tax planning United States. http://id.loc.gov/authorities/subjects/sh2008112546","Tax planning. fast http://id.worldcat.org/fast/1143815"],
+  "toplevel_subject_f":["Business enterprises","Business enterprises","United States","Tax planning","Tax planning"],
+  "call_number_xfacet":["{\"raw\":\"KF6450 .C59 1989\"}"],
+  "language_f_stored":["English"],
+  "language_search":["English"],
+  "library_f_stored":["LIBRA"],
+  "specific_location_f_stored":["LIBRA"],
+  "classification_f_stored":["K - Law"],
+  "title_1_search":["The Coopers & Lybrand guide to business tax strategies and planning /"],
+  "title_2_search":["The Coopers & Lybrand guide to business tax strategies and planning /","Guide to business tax strategies and planning.","Business tax strategies and planning","Tax strategies and planning."],
+  "author_creator_2_search":["Davies, Jonathan J. http://id.loc.gov/authorities/names/n82126416","Jonathan J. Davies http://id.loc.gov/authorities/names/n82126416","Coopers & Lybrand. http://id.loc.gov/authorities/names/n79063025","http://id.loc.gov/authorities/names/n79063025"],
+  "title":["The Coopers & Lybrand guide to business tax strategies and planning"],
+  "title_xfacet":["{\"raw\":{\"prefix\":\"The \",\"filing\":\"Coopers & Lybrand guide to business tax strategies and planning / \"}}"],
+  "title_nssort":["Coopers & Lybrand guide to business tax strategies and planning / The "],
+  "title_sort_tl":["Coopers & Lybrand guide to business tax strategies and planning / "],
+  "publication_a":["New York : Simon and Schuster, [1989] , ©1989"],
+  "elvl_rank_isort":[0],
+  "hld_count_isort":[1],
+  "itm_count_isort":[1],
+  "empty_hld_count_isort":[0],
+  "subject_xfacet2_input":["sBusiness enterprises--Taxation--United States","{\"val\":\"Business enterprises--Taxation\",\"prefix\":\"f\"}","{\"val\":\"United States\",\"prefix\":\"f\"}","sTax planning--United States","{\"val\":\"Tax planning\",\"prefix\":\"f\"}"],
+  "recently_added_isort":[1496742800],
+  "last_update_isort":[1654802397],
+  "publication_date_ssort":["1989"],
+  "pub_min_dtsort":["1989-01-01T00:00:00Z"],
+  "pub_max_dtsort":["1990-01-01T00:00:00Z"],
+  "content_min_dtsort":["1989-01-01T00:00:00Z"],
+  "content_max_dtsort":["1990-01-01T00:00:00Z"],
+  "publication_date_f_stored":["1980s"],
+  "publication_dr":["[1989 TO 1989]"],
+  "content_dr":["[1989 TO 1989]"],
+  "call_number_search":["KF6450 .C59 1989"],
+  "physical_holdings_json":["[{\"holding_id\":\"22418068440003681\",\"location\":\"stor\",\"classification_part\":\"KF6450\",\"item_part\":\".C59 1989\"}]"],
+  "corporate_author_search":["Coopers & Lybrand."],
+  "place_of_publication_search":["New York :"],
+  "publisher_search":["Simon and Schuster,"]
+}

data/lib/pennmarc/encoding_level.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+# MARC encoding level
+# See: https://www.oclc.org/bibformats/en/fixedfield/elvl.html
+# Not sure how this is used
+module PennMARC
+  module EncodingLevel
+    # Official MARC codes (https://www.loc.gov/marc/bibliographic/bdleader.html)
+    FULL = ' '
+    FULL_NOT_EXAMINED = '1'
+    UNFULL_NOT_EXAMINED = '2'
+    ABBREVIATED = '3'
+    CORE = '4'
+    PRELIMINARY = '5'
+    MINIMAL = '7'
+    PREPUBLICATION = '8'
+    UNKNOWN = 'u'
+    NOT_APPLICABLE = 'z'
+
+    # OCLC extension codes (https://www.oclc.org/bibformats/en/fixedfield/elvl.html)
+    OCLC_FULL = 'I'
+    OCLC_MINIMAL = 'K'
+    OCLC_BATCH_LEGACY = 'L'
+    OCLC_BATCH = 'M'
+    OCLC_SOURCE_DELETED = 'J'
+
+    RANK = {
+      # top 4 (per nelsonrr), do not differentiate among "good" records
+      FULL => 0,
+      FULL_NOT_EXAMINED => 0, # 1
+      OCLC_FULL => 0, # 2
+      CORE => 0, # 3
+      UNFULL_NOT_EXAMINED => 4,
+      ABBREVIATED => 5,
+      PRELIMINARY => 6,
+      MINIMAL => 7,
+      OCLC_MINIMAL => 8,
+      OCLC_BATCH => 9,
+      OCLC_BATCH_LEGACY => 10,
+      OCLC_SOURCE_DELETED => 11
+    }.freeze
+  end
+end

data/lib/pennmarc/enriched_marc.rb

@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+# Constants for Alma's MARC enrichment
+# MARC enrichment is performed during the Alma Publishing process
+# @see https://developers.exlibrisgroup.com/alma/apis/docs/bibs/R0VUIC9hbG1hd3MvdjEvYmlicy97bW1zX2lkfQ==/
+#   Alma documentation for these added fields
+module PennMARC
+  module EnrichedMarc
+    # terminology follows the Publishing Profile screen
+    TAG_HOLDING = 'hld'
+    TAG_ITEM = 'itm'
+    TAG_ELECTRONIC_INVENTORY = 'prt'
+    TAG_DIGITAL_INVENTORY = 'dig'
+
+    # these are 852 subfield codes; terminology comes from MARC spec
+    SUB_HOLDING_SHELVING_LOCATION = 'c'
+    SUB_HOLDING_SEQUENCE_NUMBER = '8'
+    SUB_HOLDING_CLASSIFICATION_PART = 'h'
+    SUB_HOLDING_ITEM_PART = 'i'
+
+    SUB_ITEM_CURRENT_LOCATION = 'g'
+    SUB_ITEM_CALL_NUMBER_TYPE = 'h'
+    SUB_ITEM_CALL_NUMBER = 'i'
+    SUB_ITEM_DATE_CREATED = 'q'
+
+    SUB_ELEC_PORTFOLIO_PID = 'a'
+    SUB_ELEC_ACCESS_URL = 'b'
+    SUB_ELEC_COLLECTION_NAME = 'c'
+    SUB_ELEC_COVERAGE = 'g'
+
+    # TODO: evaluate this in context of changed boundwiths processing
+    # 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.
+    SUB_BOUND_WITH_ID = 'y'
+  end
+end

data/lib/pennmarc/heading_control.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Shared values for controlling inclusion of subject or genre headings
+  module HeadingControl
+    # These codes are expected to be found in sf2 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
+                              local/osu mesh ndlsh nlksh rbbin rbgenr rbmscv rbpap rbpri rbprov rbpub rbtyp].freeze
+  end
+end

data/lib/pennmarc/helpers/citation.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Do Citation-y stuff
+  class Citation < Helper
+    class << self
+      # Field 510 contains Citations or references to published bibliographic descriptions,
+      # reviews, abstracts, or indexes of the content of the described item. Used to specify where an item has been
+      # cited or reviewed. Citations or references may be given in a brief form (i.e., using generally recognizable
+      # abbreviations, etc.). The actual text of a published description is not recorded in field 510 but rather in
+      # 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
+      def cited_in_show(record)
+        datafield_and_linked_alternate(record, '510')
+      end
+
+      # Field 524 is the Preferred Citation of Described Materials Note. It is the Format for the citation of the
+      # described materials that is preferred by the custodian. When multiple citation formats exist for the same item,
+      # each is recorded in a separate occurrence of field 524. The note is sometimes displayed and/or printed with an
+      # 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
+      def cite_as_show(record)
+        datafield_and_linked_alternate(record, '524')
+      end
+    end
+  end
+end

data/lib/pennmarc/helpers/creator.rb

@@ -0,0 +1,237 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Do Creator & Author field processing. Main methods pull from 110 and 111 fields. Display methods here no longer
+  # return data structures intended for generating "search" links, but some of the split subfield parsing remains from
+  # ported methods in case we need to replicate that functionality.
+  # @todo can there ever be multiple 100 fields?
+  #       can ǂe and ǂ4 both be used at the same time? seems to result in duplicate values
+  class Creator < Helper
+    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
+
+      # 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?
+      # @note ported from get_author_creator_1_search_values
+      # @param [MARC::Record] record
+      # @param [Hash] relator_mapping
+      # @return [Array<String>] array of author/creator values for indexing
+      def search(record, relator_mapping)
+        acc = record.fields(TAGS).map do |field|
+          pieces = field.filter_map do |sf|
+            if sf.code == 'a'
+              convert_name_order(sf.value)
+            elsif %w[a 1 4 6 8].exclude?(sf.code)
+              sf.value
+            elsif sf.code == '4'
+              relator = translate_relator(sf.value, relator_mapping)
+              next if relator.blank?
+
+              relator
+            end
+          end
+          value = join_and_squish(pieces)
+          if value.end_with?('.') || value.end_with?('-')
+            value
+          else
+            "#{value}."
+          end
+        end
+        # a second iteration over the same fields produces name entries with the names not reordered
+        acc += record.fields(TAGS).map do |field|
+          pieces = field.filter_map do |sf|
+            if !%w[4 6 8].member?(sf.code)
+              sf.value
+            elsif sf.code == '4'
+              relator = translate_relator(sf.value, relator_mapping)
+              next if relator.blank?
+
+              relator
+            end
+          end
+          value = join_and_squish(pieces)
+          if value.end_with?('.') || 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 do |sf|
+            convert_name_order(sf.value)
+          end.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
+
+      # Auxiliary Author/Creator search field
+      # @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
+
+      # 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
+      # @param [MARC::Record] record
+      # @param [Hash] relator_mapping
+      # @return [Array<String>] array of author/creator values for display
+      def values(record, relator_mapping)
+        record.fields(TAGS).map do |field|
+          name_from_main_entry(field, relator_mapping)
+        end
+      end
+
+      # Author/Creator values for display
+      # @todo ported from get_author_display - used on record show page. porting did not include 4, e or w values,
+      #       which were part of the link object as 'append' values in franklin
+      # @param [MARC::Record] record
+      # @return [Array<String>] array of author/creator values for display
+      def show(record)
+        fields = record.fields(TAGS)
+        fields += record.fields('880').select { |field| subfield_value_in?(field, '6', TAGS) }
+        fields.filter_map do |field|
+          join_subfields(field, &subfield_not_in?(%w[0 1 4 6 8 e w]))
+        end
+      end
+
+      # Author/Creator sort. Does not map and include any relator
+      # codes.
+      # @todo This includes any URI from ǂ0 which could help to disambiguate in sorts, but ǂ1 is excluded...
+      # @note ported from get_author_creator_sort_values
+      # @param [MARC::Record] record
+      # @return [String] string with author/creator value for sorting
+      def sort(record)
+        field = record.fields(TAGS).first
+        join_subfields(field, &subfield_not_in?(%w[1 4 6 8 e]))
+      end
+
+      # Author/Creator for faceting. Grabs values from a plethora of fields, joins defined subfields, then trims some
+      # punctuation (@see trim_punctuation)
+      # @todo should trim_punctuation apply to each subfield value, or the joined values? i think the joined values
+      # @note ported from author_creator_xfacet2_input - is this the best choice? check the copyField declarations -
+      #       franklin uses author_creator_f
+      # @param [MARC::Record] record
+      # @return [Array<String>] array of author/creator values for faceting
+      def facet(record)
+        source_map = {
+          100 => 'abcdjq', 110 => 'abcdjq', 111 => 'abcen',
+          700 => 'abcdjq', 710 => 'abcdjq', 711 => 'abcen',
+          800 => 'abcdjq', 810 => 'abcdjq', 811 => 'abcen'
+        }
+        source_map.flat_map do |field_num, subfields|
+          record.fields(field_num.to_s).map do |field|
+            trim_punctuation(join_subfields(field, &subfield_in?(subfields.split(''))))
+          end
+        end
+      end
+
+      # Conference for display, intended for results display
+      # @note ported from get_conference_values
+      # @param [MARC::Record] record
+      # @param [Hash] relator_map
+      # @return [Array<String>] array of conference values
+      def conference_show(record, relator_map)
+        record.fields('111').filter_map do |field|
+          name_from_main_entry field, relator_map
+        end
+      end
+
+      # Conference detailed display, intended for record show page.
+      # @note ported from get_conference_values
+      # @todo what is ǂi for?
+      # @param [MARC::Record] record
+      # @return [Array<String>] array of conference values
+      def conference_detail_show(record)
+        values = record.fields(%w[111 711]).filter_map do |field|
+          next unless field.indicator2.in? ['', ' ']
+
+          conf = if subfield_undefined? field, 'i'
+                   join_subfields field, &subfield_not_in?(%w[0 4 5 6 8 e j w])
+                 else
+                   ''
+                 end
+          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|
+          next unless subfield_value_in? field, '6', %w[111 711]
+
+          next if subfield_defined? field, 'i'
+
+          conf = join_subfields(field, &subfield_not_in?(%w[0 4 5 6 8 e j w]))
+          conf_extra = join_subfields(field, &subfield_in?(%w[4 e j w]))
+          join_and_squish [conf, conf_extra]
+        end
+      end
+
+      # @todo this supports "Conference" fielded search and may not be needed
+      # @note see get_conference_search_values
+      def conference_search(record); end
+
+      private
+
+      # Trim punctuation method extracted from Traject macro, to ensure consistent output
+      # @todo move to Util?
+      # @param [String] string
+      # @return [String] string with relevant punctuation removed
+      def trim_punctuation(string)
+        return string unless string
+
+        string = string.sub(%r{ *[ ,/;:] *\Z}, '')
+
+        # trailing period if it is preceded by at least three letters (possibly preceded and followed by whitespace)
+        string = string.sub(/( *[[:word:]]{3,})\. *\Z/, '\1')
+
+        # single square bracket characters if they are the start and/or end chars and there are no internal square
+        # brackets.
+        string = string.sub(/\A\[?([^\[\]]+)\]?\Z/, '\1')
+
+        # trim any leading or trailing whitespace
+        string.strip
+      end
+
+      # Extract the information we care about from 1xx fields, map relator codes, and use appropriate punctuation
+      # @param [MARC::Field] field
+      # @return [String] joined subfield values for value from field
+      def name_from_main_entry(field, mapping)
+        s = field.filter_map do |sf|
+          if %w[0 1 4 6 8].exclude?(sf.code)
+            " #{sf.value}"
+          elsif sf.code == '4'
+            relator = translate_relator(sf.value, mapping)
+            next if relator.blank?
+
+            ", #{relator}"
+          end
+        end.join
+        (s + (!%w[. -].member?(s.last) ? '.' : '')).squish
+      end
+
+      # Convert "Lastname, First" to "First Lastname"
+      # @param [String] name value for processing
+      # @return [String]
+      def convert_name_order(name)
+        return name unless name.include? ','
+
+        after_comma = join_and_squish([trim_trailing(:comma, substring_after(name, ', '))])
+        before_comma = substring_before(name, ', ')
+        "#{after_comma} #{before_comma}".squish
+      end
+    end
+  end
+end

data/lib/pennmarc/helpers/database.rb

@@ -0,0 +1,89 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Parses Database Subject Category and Database Type local fields
+  class Database < Helper
+    # Database format type used to facet databases, found in
+    # {https://upennlibrary.atlassian.net/wiki/spaces/ALMA/pages/323912493/Local+9XX+Field+Use+in+Almalocal
+    # local field 944} subfield 'a'.
+    DATABASES_FACET_VALUE = 'Database & Article Index'
+    # Penn Libraries' Community of Interest code used in
+    # {https://upennlibrary.atlassian.net/wiki/spaces/ALMA/pages/323912493/Local+9XX+Field+Use+in+Almalocal
+    # local field 943} subfield '2'.
+    COI_CODE = 'penncoi'
+
+    class << self
+      # Retrieves database subtype (subfield 'b') from
+      # {https://upennlibrary.atlassian.net/wiki/spaces/ALMA/pages/323912493/Local+9XX+Field+Use+in+Almalocal
+      # local field 944}. Only returns database subtype if Penn's Database facet value is present in subfield 'a'.
+      # @param [Marc::Record]
+      # @return [Array<string>] Array of types
+      def type(record)
+        record.fields('944').filter_map do |field|
+          # skip unless specified database format type present
+          next unless subfield_value?(field, 'a', /#{DATABASES_FACET_VALUE}/)
+
+          type = field.find { |subfield| subfield.code == 'b' }
+          type&.value
+        end
+      end
+
+      # Retrieves database subject category/communities of interest (subfield 'a') from
+      # {https://upennlibrary.atlassian.net/wiki/spaces/ALMA/pages/323912493/Local+9XX+Field+Use+in+Almalocal
+      # local field 943}. Only returns database subject category if Penn's Community of Interest code is present in
+      # subfield '2'.
+      # @param [Marc::Record]
+      # @return [Array<string>] Array of categories
+      def db_category(record)
+        return [] unless curated_db?(record)
+
+        record.fields('943').filter_map do |field|
+          # skip unless Community of Interest code is in subfield '2'
+          next unless subfield_value?(field, '2', /#{COI_CODE}/)
+
+          category = field.find { |subfield| subfield.code == 'a' }
+          category&.value
+        end
+      end
+
+      # Concatenates database subject category with database sub subject category in the format "category--subcategory"
+      # if both values are present.
+      # Retrieves both values respectively from subfield 'a' and subfield 'b' of
+      # {https://upennlibrary.atlassian.net/wiki/spaces/ALMA/pages/323912493/Local+9XX+Field+Use+in+Almalocal
+      # local field 943}. Only returns subcategory if Penn's Community of Interest code is present in subfield '2'.
+      # @note return value differs from legacy implementation. This version only returns ["category--subcategory"] or
+      #   an empty array.
+      # @param [Marc::Record]
+      # @return [Array<string>] Array of "category--subcategory"
+      def db_subcategory(record)
+        return [] unless curated_db?(record)
+
+        record.fields('943').filter_map do |field|
+          # skip unless Community of Interest code is in subfield '2'
+          next unless subfield_value?(field, '2', /#{COI_CODE}/)
+
+          category = field.find { |subfield| subfield.code == 'a' }
+
+          # skip unless category is present
+          next unless category.present?
+
+          subcategory = field.find { |subfield| subfield.code == 'b' }
+
+          # skip unless subcategory is present
+          next unless subcategory.present?
+
+          "#{category.value}--#{subcategory.value}"
+        end
+      end
+
+      private
+
+      # Determines if Database format type is format type used to facet databases
+      # @param [Marc::Record]
+      # @return [TrueClass, FalseClass]
+      def curated_db?(record)
+        record.fields('944').any? { |field| subfield_value?(field, 'a', /#{DATABASES_FACET_VALUE}/) }
+      end
+    end
+  end
+end

data/lib/pennmarc/helpers/date.rb

@@ -0,0 +1,85 @@
+# frozen_string_literal: true
+
+module PennMARC
+  # Parser methods for extracting date info as DateTime objects
+  class Date < Helper
+    class << self
+      # Retrieve publication date (Date 1) from {https://www.loc.gov/marc/bibliographic/bd008a.html 008 field}.
+      # Publication date is a four-digit year found in position 7-10 and may contain 'u' characters to represent
+      # partially known dates. We replace any occurrences of 'u' with '0' before converting to DateTime object.
+      # @param [MARC::Record] record
+      # @return [DateTime, nil] The publication date, or nil if date found in record is invalid
+      def publication(record)
+        record.fields('008').filter_map do |field|
+          four_digit_year = sanitize_partially_known_date(field.value[7, 4], '0')
+
+          next unless four_digit_year.present?
+
+          DateTime.new(four_digit_year.to_i)
+        end.first
+      end
+
+      # Retrieve date added (subfield 'q') from enriched marc 'itm' field.
+      # {PennMARC::EnrichedMarc} maps enriched marc fields and subfields created during Alma publishing.
+      # @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 do |field|
+          field.filter_map do |subfield|
+            # skip unless field has date created subfield
+            next unless subfield_defined?(field, EnrichedMarc::SUB_ITEM_DATE_CREATED)
+
+            # 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)
+
+          rescue StandardError => e
+            puts "Error parsing date in date added subfield: #{subfield.value} - #{e}"
+            nil
+          end
+        end.max
+      end
+
+      # Retrieve date last updated from {https://www.loc.gov/marc/bibliographic/bd005.html 005 field}.
+      # Date last updated is a sixteen character String recorded in
+      # {https://www.iso.org/iso-8601-date-and-time-format.html ISO 8601} format.
+      # @param [MARC::Record] record
+      # @return [DateTime, nil] The date last updated, or nil if date found in record is invalid
+      def last_updated(record)
+        record.fields('005').filter_map do |field|
+          date_time_string = field.value
+
+          next if date_time_string.blank?
+
+          next if date_time_string.start_with?('0000')
+
+          DateTime.iso8601(date_time_string).to_datetime
+
+        rescue ArgumentError => e
+          puts "Error parsing last updated date: #{date_time_string} - #{e}"
+          nil
+        end.first
+      end
+
+      private
+
+      # Sanitizes a partially known date string by replacing any 'u' occurrences with a specified replacement value.
+      # @param [String] date The date string in '%Y' format, potentially containing 'u' characters.
+      # @param [String] replacement The value with which to replace 'u' occurrences in the date string.
+      # @return [String, nil] The sanitized date string with 'u' characters replaced by the replacement value,
+      #   or nil if the date string does not match the expected format.
+      def sanitize_partially_known_date(date, replacement)
+        # early return unless date begins with zero or more digits followed by zero or more occurrences of 'u'
+        return unless /^[0-9]*u*$/.match?(date)
+
+        # replace 'u' occurrences with the specified replacement value
+        date.gsub(/u/, replacement)
+      end
+    end
+  end
+end