obp-access 0.1.2 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2c24712820162a6dab6e7bca8d6df7f58635fcb07866b239e104092f94c8c813
-  data.tar.gz: c724572b57754c8f1d4804c038b6a8664c34bf8bd6e2b9228c440b192be05368
+  metadata.gz: 3b3fda155513c49b50f81b401262456e78f63e55fb0ced23f8a54bf4577ee0af
+  data.tar.gz: 75070c8db35ae812f69f19bb55e536c9c9b3da5ec29a5846bd9d9cd53e6d5f2a
 SHA512:
-  metadata.gz: 9216dfe8b1881f9cdf299b472c8de1ae061ddeb8b7ffcb9f5c8bf793c44342e6f768e8d99497644eee8ca61f8f610b0a4dd961dda23294859710ae80d7dda2cf
-  data.tar.gz: ffdb6ac594b50d198b2d5d55e45fbf14dde2f148c17829b0cb6ea9a30134ee584a6b81597ffd589d8fad37ce348a5efc62ba82d47a9c8c544ebb01fad83e2451
+  metadata.gz: fcf54d0abc492eae8542e14e3313199be54bce5eb45fd454996a3c69dc8d5c7641a8a4bd58bbde701320c142d051ab186441b4ce47d39f47dba1774d6b329562
+  data.tar.gz: c19c3f486740f899e6e0ecad8479f78f34a7c9cf3cad8638c2eb5344408a2047e3f6f8e7222e31ea57ac7e1c79047709466c23795872c6bf238e8b076a31e77f

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-05-12 09:41:56 UTC using RuboCop version 1.86.1.
+# on 2026-06-15 08:31:30 UTC using RuboCop version 1.86.1.
 # 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
@@ -11,23 +11,9 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'obp-access.gemspec'
 
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
-# URISchemes: http, https
-Layout/LineLength:
-  Max: 124
-
 # Offense count: 3
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
     - 'lib/obp/access/elements/bibliography/bib_ref.rb'
     - 'lib/obp/access/elements/root.rb'
-
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
-# URISchemes: http, https
-Layout/LineLength:
-  Max: 124

data/README.adoc

@@ -82,7 +82,7 @@ $ obp-access fetch -l fr,de -o output/ iso:std:iso:5598:ed-3:v1:en
 The output is NISO STS XML with TBX-Basic terminology markup:
 
 * Terms use `<tbx:termEntry>` with `<tbx:langSet>` per language
-* Grammar is encoded via `<tbx:gram>` (gender: m/f/n) and `<tbx:partOfSpeech>`
+* Grammar is encoded via `<tbx:grammaticalGender>` (values: masculine/feminine/neuter) and `<tbx:partOfSpeech>`
 * Domains are extracted as `<tbx:subjectField>`
 * Deprecated terms use `<tbx:normativeAuthorization value="deprecatedTerm"/>`
 

data/lib/obp/access/elements/figure.rb

@@ -8,7 +8,7 @@ module Obp
           end
 
           def match_node?
-            super && node.css("img").any?
+            super && node.css("img").one?
           end
 
           private

data/lib/obp/access/elements/figure_group.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
@@ -16,29 +18,30 @@ module Obp
           def content
             Nokogiri::XML::Builder.new do |xml|
               xml.public_send(:"fig-group") do
-                render_caption(xml, node)
+                render_caption_from(xml, node)
                 node.css("img").each { |img| render_figure(xml, img) }
               end
             end
           end
 
-          def render_caption(xml, children)
-            xml.label children.at(".sts-caption-label").content
-            xml.caption do
-              xml.title children.at(".sts-caption-title").content
-            end
-          end
-
           def render_figure(xml, img)
             xml.fig do
-              div = img.previous
-              xml.label div.at(".sts-caption-label").content
-              xml.caption do
-                xml.title div.at(".sts-caption-title").content
-              end
+              # OBP HTML often places no caption between grouped imgs; guard accordingly.
+              render_caption_from(xml, img.previous_element) if img.previous_element
               xml.graphic("xlink:href": local_image_path(img))
             end
           end
+
+          def render_caption_from(xml, source)
+            label = source&.at(".sts-caption-label")
+            title = source&.at(".sts-caption-title")
+            xml.label label.content if label
+            return unless title
+
+            xml.caption do
+              xml.title title.content
+            end
+          end
         end
       end
     end

data/lib/obp/access/elements/terminology/base.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
@@ -15,10 +17,6 @@ module Obp
             def path_suffix
               "/tbx:termEntry/tbx:langSet"
             end
-
-            def bold_term?(node)
-              node.inner_html.start_with?("<b>") || node.inner_html.include?("<b>")
-            end
           end
         end
       end

data/lib/obp/access/elements/terminology/tig.rb

@@ -1,9 +1,13 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
       class Elements
         class Terminology
           class Tig < Base
+            NORMATIVE_AUTHORIZATION = "preferredTerm"
+
             def self.classes
               %w[sts-tbx-term]
             end
@@ -11,15 +15,16 @@ module Obp
             private
 
             def id
-              node.parent.at_css("div.sts-tbx-label").text.strip
+              node.parent.at_css("div.sts-tbx-label")&.text&.strip || ""
             end
 
             def index
-              node.path.match(/\[(\d+)\](?=\z)/)[1].to_i - 1
+              match = node.path.match(/\[(\d+)\](?=\z)/)
+              match ? match[1].to_i - 1 : 0
             end
 
             def normative_authorization
-              bold_term?(node) ? "admittedTerm" : "preferredTerm"
+              self.class::NORMATIVE_AUTHORIZATION
             end
 
             def content
@@ -46,7 +51,7 @@ module Obp
               return unless genders.any?
 
               genders.each do |gender|
-                xml.public_send(:"tbx:gram", value: gender, type: "gender")
+                xml.public_send(:"tbx:grammaticalGender", value: gender)
               end
             end
           end

data/lib/obp/access/elements/terminology/tig_admitted.rb

@@ -1,18 +1,16 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
       class Elements
         class Terminology
           class TigAdmitted < Tig
+            NORMATIVE_AUTHORIZATION = "admittedTerm"
+
             def self.classes
               %w[sts-tbx-term admittedTerm]
             end
-
-            private
-
-            def normative_authorization
-              "admittedTerm"
-            end
           end
         end
       end

data/lib/obp/access/elements/terminology/tig_deprecated.rb

@@ -1,27 +1,19 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
       class Elements
         class Terminology
           class TigDeprecated < Tig
+            NORMATIVE_AUTHORIZATION = "deprecatedTerm"
+
             def self.classes
               %w[sts-tbx-term deprecatedTerm]
             end
 
             private
 
-            def normative_authorization
-              "deprecatedTerm"
-            end
-
-            def content
-              Nokogiri::XML::Builder.new do |xml|
-                xml.public_send(:"tbx:tig", id: "term_#{id}-#{index}") do
-                  render_tig_content(xml)
-                end
-              end
-            end
-
             def parsed_html
               strip_deprecation_label(node.inner_html)
             end

data/lib/obp/access/elements/terminology/tig_preferred.rb

@@ -1,18 +1,16 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class Renderer
       class Elements
         class Terminology
           class TigPreferred < Tig
+            NORMATIVE_AUTHORIZATION = "preferredTerm"
+
             def self.classes
               %w[sts-tbx-term preferredTerm]
             end
-
-            private
-
-            def normative_authorization
-              "preferredTerm"
-            end
           end
         end
       end

data/lib/obp/access/grammar_parser.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Obp
   class Access
     class GrammarParser
@@ -9,18 +11,22 @@ module Obp
         "verb" => "verb",
       }.freeze
 
-      GENDER_VALUES = %w[m f n].freeze
+      GENDER_MAP = {
+        "m" => "masculine",
+        "f" => "feminine",
+        "n" => "neuter",
+      }.freeze
 
       BOLD_PATTERNS = [
         [->(t) { POS_MAP.key?(t) }, :handle_pos_marker],
-        [->(t) { GENDER_VALUES.include?(t) }, :handle_gender_marker],
+        [->(t) { GENDER_MAP.key?(t) }, :handle_gender_marker],
         [->(t) { t.match?(/\A[mfn],\z/) }, :handle_gender_with_comma],
         [->(t) { t.match?(/\A[mfn][,\s]+[mfn]([,\s]+[mfn])*\z/) }, :handle_multi_gender],
         [->(t) { t == "," }, :handle_comma],
-        [->(t) { t == "〈" },                     :handle_enter_bracket],
-        [->(t) { t == "〉" },                     :handle_exit_bracket],
-        [->(t) { t.match?(/\A[mfn]\s+/) },       :handle_gender_qualifier],
-        [->(t) { t.match?(/,.+[mfn]\z/) },       :handle_term_with_gender],
+        [->(t) { t == "〈" }, :handle_enter_bracket],
+        [->(t) { t == "〉" }, :handle_exit_bracket],
+        [->(t) { t.match?(/\A[mfn]\s+/) }, :handle_gender_qualifier],
+        [->(t) { t.match?(/,.+[mfn]\z/) }, :handle_term_with_gender],
       ].freeze
 
       def self.parse(inner_html)
@@ -60,15 +66,15 @@ module Obp
         end
 
         def handle_gender_marker(text, state)
-          state[:genders] << text.strip
+          add_gender(state, text.strip)
         end
 
         def handle_gender_with_comma(text, state)
-          state[:genders] << text.strip[0]
+          add_gender(state, text.strip[0])
         end
 
         def handle_multi_gender(text, state)
-          text.strip.scan(/[mfn]/).each { |g| state[:genders] << g }
+          text.strip.scan(/[mfn]/).each { |code| add_gender(state, code) }
         end
 
         def handle_enter_bracket(_text, state)
@@ -80,14 +86,14 @@ module Obp
         end
 
         def handle_gender_qualifier(text, state)
-          state[:genders] << text.strip[0]
+          add_gender(state, text.strip[0])
         end
 
         def handle_term_with_gender(text, state)
           stripped = text.strip
           if stripped =~ /\A(.+),\s*([mfn])\z/
-            state[:term_parts] << $1.strip
-            state[:genders] << $2
+            state[:term_parts] << Regexp.last_match(1).strip
+            add_gender(state, Regexp.last_match(2))
           else
             state[:term_parts] << stripped
           end
@@ -105,6 +111,10 @@ module Obp
 
         def handle_skip(_text, _state); end
 
+        def add_gender(state, code)
+          state[:genders] << GENDER_MAP.fetch(code)
+        end
+
         def parse_segments(html)
           segments = []
           remaining = html.dup

data/lib/obp/access/version.rb

@@ -1,5 +1,5 @@
 module Obp
   class Access
-    VERSION = "0.1.2".freeze
+    VERSION = "0.1.4".freeze
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: obp-access
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-12 00:00:00.000000000 Z
+date: 2026-06-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri