stanford-mods 2.2.0 → 2.2.1

data/lib/stanford-mods.rb

@@ -2,6 +2,7 @@ require 'mods'
 require 'stanford-mods/date_parsing'
 require 'stanford-mods/coordinate'
 require 'stanford-mods/geo_spatial'
+require 'stanford-mods/geo_utils'
 require 'stanford-mods/imprint'
 require 'stanford-mods/name'
 require 'stanford-mods/origin_info'

data/lib/stanford-mods/coordinate.rb

@@ -4,26 +4,28 @@ module Stanford
     ##
     # Geospatial coordinate parsing
     class Coordinate
+      require 'stanford-mods/geo_utils'
+      include ::Stanford::Mods::GeoUtils
+
       attr_reader :value
 
       def initialize(value)
         @value = value
       end
 
-      # Convert the coordinate to a WKT/CQL ENVELOPE representation
+      # @return [String] the coordinate in WKT/CQL ENVELOPE representation
       def as_envelope
         return unless valid?
-
         "ENVELOPE(#{bounds[:min_x]}, #{bounds[:max_x]}, #{bounds[:max_y]}, #{bounds[:min_y]})"
       end
 
-      # Convert the coordinate to a Solr 4.x bbox-format representation
+      # @return [String] the coordinate in Solr 4.x+ bbox-format representation
       def as_bbox
         return unless valid?
-
         "#{bounds[:min_x]} #{bounds[:min_y]} #{bounds[:max_x]} #{bounds[:max_y]}"
       end
 
+      # @return [Boolean] true iff the coordinates are geographically valid
       def valid?
         return false if bounds.empty?
 
@@ -40,42 +42,18 @@ module Stanford
 
       def bounds
         @bounds ||= begin
-          matches = coord.match %r{\A(?<lat>[EW].+-+.+)\s*/\s*(?<lng>[NS].+-+.+)\Z}
-
-          if matches
-            min_x, max_x = matches['lat'].split(/-+/).map { |x| coord_to_decimal(x) }.minmax
-            min_y, max_y = matches['lng'].split(/-+/).map { |y| coord_to_decimal(y) }.minmax
-
-            { min_x: min_x, min_y: min_y, max_x: max_x, max_y: max_y }
-          else
-            {}
-          end
+          matches = cleaner_coordinate(value).match %r{\A(?<lat>[EW].+-+.+)\s*/\s*(?<lng>[NS].+-+.+)\Z}
+          return {} unless matches
+          min_x, max_x = matches['lat'].split(/-+/).map { |x| coord_to_decimal(x) }.minmax
+          min_y, max_y = matches['lng'].split(/-+/).map { |y| coord_to_decimal(y) }.minmax
+          { min_x: min_x, min_y: min_y, max_x: max_x, max_y: max_y }
         end
       end
 
+      # @deprecated see GeoUtils
       def coord
-        matches = value.match(/^\(?([^)]+)\)?\.?$/)
-
-        if matches
-          matches[1]
-        else
-          value
-        end
-      end
-
-      def coord_to_decimal(point)
-        regex = /(?<dir>[NESW])\s*(?<deg>\d+)[°⁰º](?:(?<min>\d+)[ʹ'])?(?:(?<sec>\d+)[ʺ"])?/
-        match = regex.match(point)
-
-        return Float::INFINITY unless match
-
-        dec = match['deg'].to_i
-        dec += match['min'].to_f / 60
-        dec += match['sec'].to_f / 60 / 60
-        dec = -1 * dec if match['dir'] == 'W' || match['dir'] == 'S'
-
-        dec
+        cleaner_coordinate(value)
       end
     end
   end
-end
+end

data/lib/stanford-mods/date_parsing.rb

@@ -6,7 +6,6 @@ module Stanford
     #     - we may want an integer or date sort field as well as lexical
     #     - we could add methods like my_date.bc?
     class DateParsing
-
       # get display value for year, generally an explicit year or "17th century" or "5 B.C." or "1950s" or '845 A.D.'
       # @return [String, nil] display value for year if we could parse one, nil otherwise
       def self.date_str_for_display(date_str)
@@ -196,7 +195,7 @@ module Stanford
       # @return [String, nil] yy00 if orig_date_str matches pattern, nil otherwise; also nil if B.C. in pattern
       def sortable_year_for_century
         return unless orig_date_str
-        return if orig_date_str.match(/B\.C\./)
+        return if orig_date_str =~ /B\.C\./
         century_matches = orig_date_str.match(CENTURY_4CHAR_REGEXP)
         if century_matches
           return $1 + '00' if $1.length == 2
@@ -215,7 +214,7 @@ module Stanford
       # @return [String, nil] yy(th) Century if orig_date_str matches pattern, nil otherwise; also nil if B.C. in pattern
       def display_str_for_century
         return unless orig_date_str
-        return if orig_date_str.match(/B\.C\./)
+        return if orig_date_str =~ /B\.C\./
         century_str_matches = orig_date_str.match(CENTURY_WORD_REGEXP)
         return century_str_matches.to_s if century_str_matches
 
@@ -263,7 +262,7 @@ module Stanford
       # @return [String, nil] String sortable -ddd if orig_date_str matches pattern; nil otherwise
       def sortable_year_str_for_early_numeric
         return unless orig_date_str.match(EARLY_NUMERIC)
-        if orig_date_str.match(/^\-/)
+        if orig_date_str =~ /^\-/
           # negative number becomes x - 1000 for sorting; -005 for -995
           num = orig_date_str[1..-1].to_i - 1000
           return '-' + num.to_s[1..-1].rjust(3, '0')
@@ -276,7 +275,7 @@ module Stanford
       # @return [Integer, nil] Integer sortable -ddd if orig_date_str matches pattern; nil otherwise
       def sortable_year_int_for_early_numeric
         return orig_date_str.to_i if orig_date_str.match(EARLY_NUMERIC)
-        orig_date_str.to_i if orig_date_str.match(/^-\d{4}$/)
+        orig_date_str.to_i if orig_date_str =~ /^-\d{4}$/
       end
 
       # get display value for date String containing yyy, yy, y, -y, -yy, -yyy
@@ -290,7 +289,7 @@ module Stanford
         # return 1 B.C. when the date is 0 since there is no 0 year
         return '1 B.C.' if orig_date_str == '0'
         # negative number becomes B.C.
-        return  "#{orig_date_str[1..-1].to_i + 1} B.C." if orig_date_str.match(/^\-/)
+        return "#{orig_date_str[1..-1].to_i + 1} B.C." if orig_date_str =~ /^\-/
         # remove leading 0s from early dates
         "#{orig_date_str.to_i} A.D."
       end
@@ -301,10 +300,10 @@ module Stanford
       #   has made this method bogus.
       # @return [String, nil] sortable 4 digit year (e.g. 1865, 0950) if orig_date_str is parseable via ruby Date, nil otherwise
       def year_via_ruby_parsing
-        return unless orig_date_str.match(/\d\d/) # need at least 2 digits
+        return unless orig_date_str =~ /\d\d/ # need at least 2 digits
         # need more in string than only 2 digits
         return if orig_date_str.match(/^\d\d$/) || orig_date_str.match(/^\D*\d\d\D*$/)
-        return if orig_date_str.match(/\d\s*B.C./) # skip B.C. dates
+        return if orig_date_str =~ /\d\s*B.C./ # skip B.C. dates
         date_obj = Date.parse(orig_date_str)
         date_obj.year.to_s
       rescue ArgumentError

data/lib/stanford-mods/geo_spatial.rb

@@ -1,29 +1,49 @@
 # encoding: UTF-8
-require 'logger'
 require 'mods'
 
 module Stanford
   module Mods
     # NON-SearchWorks specific wranglings of MODS cartographics metadata
     class Record < ::Mods::Record
+      GMLNS = 'http://www.opengis.net/gml/3.2/'.freeze
+
+      # @return [Array{String}] subject cartographic coordinates values
       def coordinates
-        Array(@mods_ng_xml.subject.cartographics.coordinates).map(&:text)
+        Array(mods_ng_xml.subject.cartographics.coordinates).map(&:text)
       end
 
-      def coordinates_as_envelope
-        coordinates.map do |n|
-          c = Stanford::Mods::Coordinate.new(n)
+      # @return [Array{String}] values suitable for solr SRPT fields, like "ENVELOPE(-16.0, 28.0, 13.0, -15.0)"
+      # @note example xml leaf nodes
+      #  <gml:lowerCorner>-122.191292 37.4063388</gml:lowerCorner>
+      #  <gml:upperCorner>-122.149475 37.4435369</gml:upperCorner>
+      def geo_extensions_as_envelope
+        mods_ng_xml.extension
+                    .xpath('//rdf:RDF/rdf:Description/gml:boundedBy/gml:Envelope',
+                      'gml' => GMLNS,
+                      'rdf' => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'
+                    ).map do |v|
+                      uppers = v.xpath('gml:upperCorner', 'gml' => GMLNS).text.split
+                      lowers = v.xpath('gml:lowerCorner', 'gml' => GMLNS).text.split
+                      "ENVELOPE(#{lowers[0]}, #{uppers[0]}, #{uppers[1]}, #{lowers[1]})"
+                    end
+      rescue RuntimeError => e
+        logger.warn "failure parsing <extension> element: #{e.message}"
+        []
+      end
 
-          c.as_envelope if c.valid?
-        end.compact
+      # @return [Array{Stanford::Mods::Coordinate}] valid coordinates as objects
+      def coordinates_objects
+        coordinates.map { |n| Stanford::Mods::Coordinate.new(n) }.select(&:valid?)
       end
 
-      def coordinates_as_bbox
-        coordinates.map do |n|
-          c = Stanford::Mods::Coordinate.new(n)
+      # @return [Array{String}] values suitable for solr SRPT fields, like "ENVELOPE(-16.0, 28.0, 13.0, -15.0)"
+      def coordinates_as_envelope
+        coordinates_objects.map(&:as_envelope).compact
+      end
 
-          c.as_bbox if c.valid?
-        end.compact
+      # @return [Array{String}] with 4-part space-delimted strings, like "-16.0 -15.0 28.0 13.0"
+      def coordinates_as_bbox
+        coordinates_objects.map(&:as_bbox).compact
       end
 
       alias point_bbox coordinates_as_bbox

data/lib/stanford-mods/geo_utils.rb

@@ -0,0 +1,28 @@
+# encoding: utf-8
+module Stanford
+  module Mods
+    # Abstract geo methods usable to several classes
+    module GeoUtils
+      # @param [String] val Coordinates value
+      # @return [String] cleaned value (strips parens and period), or the original value
+      def cleaner_coordinate(val)
+        matches = val.match(/^\(?([^)]+)\)?\.?$/)
+        matches ? matches[1] : val
+      end
+
+      # @param [String] point coordinate point in degrees notation
+      # @return [Float] converted value in decimal notation
+      def coord_to_decimal(point)
+        regex = /(?<dir>[NESW])\s*(?<deg>\d+)[°⁰º](?:(?<min>\d+)[ʹ'])?(?:(?<sec>\d+)[ʺ"])?/
+        match = regex.match(point)
+        return Float::INFINITY unless match
+
+        dec = match['deg'].to_i
+        dec += match['min'].to_f / 60
+        dec += match['sec'].to_f / 60 / 60
+        dec = -1 * dec if match['dir'] == 'W' || match['dir'] == 'S'
+        dec
+      end
+    end
+  end
+end

data/lib/stanford-mods/imprint.rb

@@ -354,7 +354,7 @@ module Stanford
           century_matches = orig_date_str.match(CENTURY_4CHAR_REGEXP) if orig_date_str
           if century_matches
             require 'active_support/core_ext/integer/inflections'
-            new_century_str =  "#{(century_matches[3].to_i + 1).ordinalize} century"
+            new_century_str = "#{(century_matches[3].to_i + 1).ordinalize} century"
             my_ng_date_element.content = "#{century_matches[1]}#{new_century_str}#{century_matches[4]}"
           else
             my_ng_date_element.content

data/lib/stanford-mods/name.rb

@@ -1,13 +1,10 @@
 # encoding: UTF-8
-require 'logger'
 require 'mods'
 
 # NON-SearchWorks specific wranglings of MODS <name> metadata as a mixin to the Stanford::Mods::Record object
 module Stanford
   module Mods
-
     class Record < ::Mods::Record
-
       # the first encountered <mods><name> element with marcrelator flavor role of 'Creator' or 'Author'.
       # if no marcrelator 'Creator' or 'Author', the first name without a role.
       # if no name without a role, then nil
@@ -16,10 +13,8 @@ module Stanford
       def main_author_w_date
         result = nil
         first_wo_role = nil
-        @mods_ng_xml.plain_name.each { |n|
-          if n.role.size == 0
-            first_wo_role ||= n
-          end
+        mods_ng_xml.plain_name.each { |n|
+          first_wo_role ||= n if n.role.empty?
           n.role.each { |r|
             if r.authority.include?('marcrelator') &&
                   (r.value.include?('Creator') || r.value.include?('Author'))
@@ -27,9 +22,7 @@ module Stanford
             end
           }
         }
-        if !result && first_wo_role
-          result = first_wo_role.display_value_w_date
-        end
+        result = first_wo_role.display_value_w_date if !result && first_wo_role
         result
       end # main_author
 
@@ -38,7 +31,7 @@ module Stanford
       #  see Mods::Record.name  in nom_terminology for details on the display_value algorithm
       def additional_authors_w_dates
         results = []
-        @mods_ng_xml.plain_name.each { |n|
+        mods_ng_xml.plain_name.each { |n|
           results << n.display_value_w_date
         }
         results.delete(main_author_w_date)
@@ -50,7 +43,7 @@ module Stanford
       # FIXME:  this is broken if there are multiple role codes and some of them are not marcrelator
       def non_collector_person_authors
         result = []
-        @mods_ng_xml.personal_name.map do |n|
+        mods_ng_xml.personal_name.map do |n|
           next if n.role.size.zero?
           n.role.each { |r|
             result << n.display_value_w_date unless includes_marc_relator_collector_role?(r)
@@ -63,7 +56,7 @@ module Stanford
       #  a personal name with the role of Collector (see mods gem nom_terminology for display value algorithm)
       def collectors_w_dates
         result = []
-        @mods_ng_xml.personal_name.each do |n|
+        mods_ng_xml.personal_name.each do |n|
           next if n.role.size.zero?
           n.role.each { |r|
             result << n.display_value_w_date if includes_marc_relator_collector_role?(r)
@@ -72,7 +65,7 @@ module Stanford
         result unless result.empty?
       end
 
-      COLLECTOR_ROLE_URI = 'http://id.loc.gov/vocabulary/relators/col'
+      COLLECTOR_ROLE_URI = 'http://id.loc.gov/vocabulary/relators/col'.freeze
 
       # @param Nokogiri::XML::Node role_node the role node from a parent name node
       # @return true if there is a MARC relator collector role assigned
@@ -80,7 +73,6 @@ module Stanford
         (role_node.authority.include?('marcrelator') && role_node.value.include?('Collector')) ||
         role_node.roleTerm.valueURI.first == COLLECTOR_ROLE_URI
       end
-
     end # class Record
   end # Module Mods
 end # Module Stanford

data/lib/stanford-mods/origin_info.rb

@@ -1,4 +1,3 @@
-require 'logger'
 require 'mods'
 
 # Parsing MODS /originInfo for Publication/Imprint data:
@@ -11,7 +10,6 @@ require 'mods'
 module Stanford
   module Mods
     class Record < ::Mods::Record
-
       # return pub year as an Integer
       # prefer dateIssued (any) before dateCreated (any) before dateCaptured (any)
       #  look for a keyDate and use it if there is one;  otherwise pick earliest date
@@ -56,26 +54,26 @@ module Stanford
         # get_main_title_date
         # https://github.com/sul-dlss/SearchWorks/blob/7d4d870a9d450fed8b081c38dc3dbd590f0b706e/app/helpers/results_document_helper.rb#L8-L46
 
-        #"publication_year_isi"   => "Publication date",  <--  do it already
-        #"beginning_year_isi"     => "Beginning date",
-        #"earliest_year_isi"      => "Earliest date",
-        #"earliest_poss_year_isi" => "Earliest possible date",
-        #"ending_year_isi"        => "Ending date",
-        #"latest_year_isi"        => "Latest date",
-        #"latest_poss_year_isi"   => "Latest possible date",
-        #"production_year_isi"    => "Production date",
-        #"original_year_isi"      => "Original date",
-        #"copyright_year_isi"     => "Copyright date"} %>
+        # "publication_year_isi"   => "Publication date",  <--  do it already
+        # "beginning_year_isi"     => "Beginning date",
+        # "earliest_year_isi"      => "Earliest date",
+        # "earliest_poss_year_isi" => "Earliest possible date",
+        # "ending_year_isi"        => "Ending date",
+        # "latest_year_isi"        => "Latest date",
+        # "latest_poss_year_isi"   => "Latest possible date",
+        # "production_year_isi"    => "Production date",
+        # "original_year_isi"      => "Original date",
+        # "copyright_year_isi"     => "Copyright date"} %>
 
-        #"creation_year_isi"      => "Creation date",  <--  do it already
-        #{}"release_year_isi"       => "Release date",
-        #{}"reprint_year_isi"       => "Reprint/reissue date",
-        #{}"other_year_isi"         => "Date",
+        # "creation_year_isi"      => "Creation date",  <--  do it already
+        # {}"release_year_isi"       => "Release date",
+        # {}"reprint_year_isi"       => "Reprint/reissue date",
+        # {}"other_year_isi"         => "Date",
       end
 
       # @return [String] single String containing imprint information for display
       def imprint_display_str
-        imp = Stanford::Mods::Imprint.new(self.origin_info)
+        imp = Stanford::Mods::Imprint.new(origin_info)
         imp.display_str
       end
 
@@ -116,8 +114,8 @@ module Stanford
       # @param [Boolean] ignore_approximate true if approximate dates (per qualifier attribute)
       #   should be excluded; false approximate dates should be included
       # @return [Array<Nokogiri::XML::Element>]
-      def date_created_elements(ignore_approximate=false)
-        date_created_nodeset = @mods_ng_xml.origin_info.dateCreated
+      def date_created_elements(ignore_approximate = false)
+        date_created_nodeset = mods_ng_xml.origin_info.dateCreated
         return self.class.remove_approximate(date_created_nodeset) if ignore_approximate
         date_created_nodeset.to_a
       end
@@ -126,8 +124,8 @@ module Stanford
       # @param [Boolean] ignore_approximate true if approximate dates (per qualifier attribute)
       #   should be excluded; false approximate dates should be included
       # @return [Array<Nokogiri::XML::Element>]
-      def date_issued_elements(ignore_approximate=false)
-        date_issued_nodeset = @mods_ng_xml.origin_info.dateIssued
+      def date_issued_elements(ignore_approximate = false)
+        date_issued_nodeset = mods_ng_xml.origin_info.dateIssued
         return self.class.remove_approximate(date_issued_nodeset) if ignore_approximate
         date_issued_nodeset.to_a
       end
@@ -188,7 +186,7 @@ module Stanford
         result = send(method_sym, date_issued_elements(ignore_approximate))
         result ||= send(method_sym, date_created_elements(ignore_approximate))
         # dateCaptured for web archive seed records
-        result ||= send(method_sym, @mods_ng_xml.origin_info.dateCaptured.to_a)
+        result ||= send(method_sym, mods_ng_xml.origin_info.dateCaptured.to_a)
         result
       end
 
@@ -208,6 +206,7 @@ module Stanford
 
       class << self
         private
+
         # get earliest parseable year from the passed date elements
         # @param [Array<Nokogiri::XML::Element>] date_el_array the elements from which to select a pub date
         # @param [Symbol] method_sym method name in DateParsing, as a symbol
@@ -226,11 +225,10 @@ module Stanford
         end
       end
 
-
 # ----   old date parsing methods used downstream of gem;  will be deprecated/replaced with new date parsing methods
 
       def place
-        vals = self.term_values([:origin_info, :place, :placeTerm])
+        vals = term_values([:origin_info, :place, :placeTerm])
         vals
       end
 
@@ -355,14 +353,14 @@ module Stanford
       def parse_dates_from_originInfo
         @dates_marc_encoding = []
         @dates_no_marc_encoding = []
-        self.origin_info.dateIssued.each { |di|
+        origin_info.dateIssued.each { |di|
           if di.encoding == "marc"
             @dates_marc_encoding << di.text
           else
             @dates_no_marc_encoding << di.text
           end
         }
-        self.origin_info.dateCreated.each { |dc|
+        origin_info.dateCreated.each { |dc|
           if dc.encoding == "marc"
             @dates_marc_encoding << dc.text
           else
@@ -393,7 +391,7 @@ module Stanford
               # look for things like '1865-6 CE'
               pos = f_date.index(Regexp.new(match + '...CE'))
               pos = pos ? pos.to_i : 0
-              if f_date.include?(match+' CE') or pos > 0
+              if f_date.include?(match + ' CE') || pos > 0
                 @pub_year = match
                 return match
               end
@@ -409,7 +407,7 @@ module Stanford
       def get_three_digit_year(dates)
         dates.each do |f_date|
           matches = f_date.scan(/\d{3}/)
-          return matches.first if matches.length > 0
+          return matches.first unless matches.empty?
         end
         nil
       end
@@ -420,7 +418,7 @@ module Stanford
       def get_bc_year(dates)
         dates.each do |f_date|
           matches = f_date.scan(/\d{3} B.C./)
-          if matches.length > 0
+          unless matches.empty?
             bc_year = matches.first[0..2]
             return (bc_year.to_i - 1000).to_s
           end
@@ -434,9 +432,9 @@ module Stanford
       def get_single_digit_century(dates)
         dates.each do |f_date|
           matches = f_date.scan(/\d{1}th/)
-          next if matches.length == 0
+          next if matches.empty?
           if matches.length == 1
-            @pub_year = ((matches.first[0, 2].to_i) - 1).to_s + '--'
+            @pub_year = (matches.first[0, 2].to_i - 1).to_s + '--'
             return @pub_year
           else
             # when there are multiple matches, check for ones with CE after them
@@ -445,7 +443,7 @@ module Stanford
               pos = pos ? pos.to_i : f_date.index(Regexp.new(match + ' century CE'))
               pos = pos ? pos.to_i : 0
               if f_date.include?(match + ' CE') || pos > 0
-                @pub_year = ((match[0, 1].to_i) - 1).to_s + '--'
+                @pub_year = (match[0, 1].to_i - 1).to_s + '--'
                 return @pub_year
               end
             end
@@ -460,9 +458,9 @@ module Stanford
       def get_double_digit_century(dates)
         dates.each do |f_date|
           matches = f_date.scan(/\d{2}th/)
-          next if matches.length == 0
+          next if matches.empty?
           if matches.length == 1
-            @pub_year=((matches.first[0, 2].to_i) - 1).to_s + '--'
+            @pub_year = (matches.first[0, 2].to_i - 1).to_s + '--'
             return @pub_year
           else
             # when there are multiple matches, check for ones with CE after them
@@ -470,8 +468,8 @@ module Stanford
               pos = f_date.index(Regexp.new(match + '...CE'))
               pos = pos ? pos.to_i : f_date.index(Regexp.new(match + ' century CE'))
               pos = pos ? pos.to_i : 0
-              if f_date.include?(match+' CE') or pos > 0
-                @pub_year = ((match[0, 2].to_i) - 1).to_s + '--'
+              if f_date.include?(match + ' CE') || pos > 0
+                @pub_year = (match[0, 2].to_i - 1).to_s + '--'
                 return @pub_year
               end
             end
@@ -497,4 +495,4 @@ module Stanford
       end
     end # class Record
   end
-end
+end