obp-access 0.1.4 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3b3fda155513c49b50f81b401262456e78f63e55fb0ced23f8a54bf4577ee0af
-  data.tar.gz: 75070c8db35ae812f69f19bb55e536c9c9b3da5ec29a5846bd9d9cd53e6d5f2a
+  metadata.gz: b11820d71fdd40bfeeddd92447062fc728a2642a3bdd4b572fcb3162bd86230a
+  data.tar.gz: 4c061e02a1ead75b4db4828d7646d69052a44ed0369bb905c9a0aafb8f064a99
 SHA512:
-  metadata.gz: fcf54d0abc492eae8542e14e3313199be54bce5eb45fd454996a3c69dc8d5c7641a8a4bd58bbde701320c142d051ab186441b4ce47d39f47dba1774d6b329562
-  data.tar.gz: c19c3f486740f899e6e0ecad8479f78f34a7c9cf3cad8638c2eb5344408a2047e3f6f8e7222e31ea57ac7e1c79047709466c23795872c6bf238e8b076a31e77f
+  metadata.gz: 819be7f79f169115d5e0c486f09e8b061ac68fb85040e764832f0280e63094893c9d2da2428395f32179fff03625906f841ed4dea4020c7aa484873170603d49
+  data.tar.gz: ae43acfe12065482d2bfb872e59b0a221416664c43415a49078b206957e5190744b3ebafd60c7f78e5bb15821f04693f876f7de5127238cdabab29af95c125d4

data/.rubocop.yml

@@ -1,18 +1,31 @@
 # Auto-generated by Cimas: Do not edit it manually!
 # See https://github.com/metanorma/cimas
 inherit_from:
+  - https://raw.githubusercontent.com/riboseinc/oss-guides/main/ci/rubocop.yml
+  # .rubocop_todo.yml MUST be the last entry. inherit_from is last-wins:
+  # if listed before oss-guides, the shared config's stricter Metrics/
+  # (MethodLength, BlockLength, etc.) rules override the todo's per-file
+  # grandfathering, and the todo becomes inert on those cops. Empirically
+  # verified on suma 2026-07-06: with todo listed first, 34 Metrics/* offenses
+  # remained; moved last, cleared. Every gem in the metanorma-org fleet
+  # already ships a `.rubocop_todo.yml` on its live tree (audited 2026-07-06,
+  # 54/54 have it), so this reference is safe to emit unconditionally.
   - .rubocop_todo.yml
-  - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
+
+# Rubocop plugins enabled centrally so every metanorma-org gem picks them up
+# on cimas sync — best practice belongs at the shared-template layer, not
+# per-repo. Per ronaldtse feedback on metanorma/ci#332.
+plugins:
+  - rubocop-rspec
+  - rubocop-performance
+  - rubocop-rake
 
 # local repo-specific modifications
 # ...
 
 AllCops:
-  NewCops: enable
-  SuggestExtensions: false
-
-Metrics/MethodLength:
-  Max: 30
-
-Layout/LineLength:
-  Max: 120
+  # 3.3 matches the org-wide minimum being pushed via #274 (Raise minimum
+  # Ruby version to 3.3 due to EOL of 3.2 on 2026-03-31). Was 3.4 before
+  # this commit — 3.4 was above the org's stated minimum and would have
+  # applied Rubocop rules that fail-close on gems still targeting 3.3.
+  TargetRubyVersion: 3.3

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-06-15 08:31:30 UTC using RuboCop version 1.86.1.
+# on 2026-07-18 01:14:30 UTC using RuboCop version 1.88.2.
 # 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
@@ -11,9 +11,116 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'obp-access.gemspec'
 
+# Offense count: 139
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
+# URISchemes: http, https
+Layout/LineLength:
+  Exclude:
+    - 'fetch_en_html.rb'
+    - 'fetch_html.rb'
+    - 'lib/obp/access/catalog.rb'
+    - 'lib/obp/access/cli.rb'
+    - 'lib/obp/access/domain_extractor.rb'
+    - 'lib/obp/access/elements/base.rb'
+    - 'lib/obp/access/elements/bibliography.rb'
+    - 'lib/obp/access/elements/figure_group.rb'
+    - 'lib/obp/access/elements/index.rb'
+    - 'lib/obp/access/elements/root.rb'
+    - 'lib/obp/access/elements/terminology/definition.rb'
+    - 'lib/obp/access/elements/terminology/example.rb'
+    - 'lib/obp/access/elements/terminology/tig.rb'
+    - 'lib/obp/access/elements/terminology/tig_deprecated.rb'
+    - 'lib/obp/access/grammar_parser.rb'
+    - 'lib/obp/access/inline_renderer.rb'
+    - 'lib/obp/access/parser.rb'
+    - 'lib/obp/access/retriever.rb'
+    - 'obp-access.gemspec'
+    - 'spec/obp/access/access_spec.rb'
+    - 'spec/obp/access/cli_spec.rb'
+    - 'spec/obp/access/deliverable_spec.rb'
+    - 'spec/obp/access/elements/bib_ref_spec.rb'
+    - 'spec/obp/access/elements/disp_formula_spec.rb'
+    - 'spec/obp/access/elements/figure_group_spec.rb'
+    - 'spec/obp/access/elements/figure_spec.rb'
+    - 'spec/obp/access/elements/footnotes_spec.rb'
+    - 'spec/obp/access/elements/index_spec.rb'
+    - 'spec/obp/access/elements/non_normative_example_spec.rb'
+    - 'spec/obp/access/elements/protected_content_note_spec.rb'
+    - 'spec/obp/access/elements/section_title_spec.rb'
+    - 'spec/obp/access/elements/table_wrap_spec.rb'
+    - 'spec/obp/access/elements/terminology/definition_spec.rb'
+    - 'spec/obp/access/elements/terminology/tig_spec.rb'
+    - 'spec/obp/access/grammar_parser_spec.rb'
+    - 'spec/obp/access/inline_renderer_spec.rb'
+    - 'spec/obp/access/retriever_spec.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Lint/SafeNavigationWithEmpty:
+  Exclude:
+    - 'lib/obp/access/elements/disp_formula.rb'
+
 # 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: 11
+# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
+Metrics/MethodLength:
+  Max: 16
+
+# Offense count: 1
+# Configuration parameters: IgnoredMetadata.
+RSpec/DescribeClass:
+  Exclude:
+    - '**/spec/features/**/*'
+    - '**/spec/requests/**/*'
+    - '**/spec/routing/**/*'
+    - '**/spec/system/**/*'
+    - '**/spec/views/**/*'
+    - 'spec/obp/access/elements/terminology/tig_spec.rb'
+
+# Offense count: 44
+# Configuration parameters: CountAsOne.
+RSpec/ExampleLength:
+  Max: 26
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+RSpec/IteratedExpectation:
+  Exclude:
+    - 'spec/obp/access/catalog_spec.rb'
+
+# Offense count: 1
+RSpec/MultipleDescribes:
+  Exclude:
+    - 'spec/obp/access/elements/terminology/tig_spec.rb'
+
+# Offense count: 65
+RSpec/MultipleExpectations:
+  Max: 11
+
+# Offense count: 14
+# Configuration parameters: CustomTransform, IgnoreMethods, IgnoreMetadata, InflectorPath, EnforcedInflector.
+# SupportedInflectors: default, active_support
+RSpec/SpecFilePathFormat:
+  Exclude:
+    - '**/spec/routing/**/*'
+    - 'spec/obp/access/access_spec.rb'
+    - 'spec/obp/access/elements/bib_ref_spec.rb'
+    - 'spec/obp/access/elements/disp_formula_spec.rb'
+    - 'spec/obp/access/elements/figure_group_spec.rb'
+    - 'spec/obp/access/elements/figure_spec.rb'
+    - 'spec/obp/access/elements/footnotes_spec.rb'
+    - 'spec/obp/access/elements/index_spec.rb'
+    - 'spec/obp/access/elements/non_normative_example_spec.rb'
+    - 'spec/obp/access/elements/protected_content_note_spec.rb'
+    - 'spec/obp/access/elements/root_spec.rb'
+    - 'spec/obp/access/elements/section_title_spec.rb'
+    - 'spec/obp/access/elements/section_type_spec.rb'
+    - 'spec/obp/access/elements/table_wrap_spec.rb'
+    - 'spec/obp/access/elements/terminology/definition_spec.rb'

data/CLAUDE.md

@@ -9,10 +9,11 @@ Ruby gem (`obp-access`) that fetches informative content (introduction, scope, t
 ## Commands
 
 - **Install dependencies:** `bundle install`
-- **Run tests:** `bundle exec rspec`
+- **Run tests:** `bundle exec rspec` (note: retriever/access-fetch specs hit the live OBP API)
 - **Lint:** `bundle exec rubocop`
 - **Run a single test:** `bundle exec rspec spec/obp/access/grammar_parser_spec.rb`
 - **Console:** `bin/console` (loads the gem for interactive use)
+- **CLI:** `bundle exec exe/obp-access` (fetch a document or all languages from OBP)
 
 ## Critical rules
 
@@ -25,13 +26,15 @@ Ruby gem (`obp-access`) that fetches informative content (introduction, scope, t
 
 Data flows through these classes in `lib/obp/access/`:
 
-1. **`Access`** (entry point) — orchestrates the pipeline. `Obp::Access.fetch(urn)` returns an instance per language. `Access.fetch_all(urn, languages:)` returns separate instances per language.
+1. **`Access`** (entry point) — orchestrates the pipeline. `Obp::Access.fetch(urn)` returns an instance per language. `Access.fetch_all(urn, languages:)` returns separate instances per language. `Access.from_html(urn:, html:, caption:, titles:)` converts an already-downloaded OBP HTML fragment with no network access (the offline path used by fixture-based tests).
 
-2. **`Parser`** — fetches content from the ISO OBP API (`https://www.iso.org/obp/ui`) via HTTP POST with a URN payload. Parses the JSON response to extract HTML content, titles, and images.
+2. **`Parser`** — fetches content from the ISO OBP API (`https://www.iso.org/obp/ui`) via HTTP POST with a URN payload. Parses the JSON response to extract HTML content, titles, and images. **`RawHtmlParser`** subclasses it and duck-types the API for pre-captured HTML.
 
-3. **`Converter`** — wraps the HTML source, normalizes whitespace, parses it with Nokogiri, and passes DOM nodes to the Renderer.
+3. **`Urn`** — parses URN identity metadata (`originator`, `doc_number` incl. part numbers like `80000:-12` → "80000-12", `doc_type` IS/TS/TR/PAS/Guide/IWA, `edition`, `version`). `Elements::Root` builds `<std-ident>` from these — never parse URN segments positionally elsewhere.
 
-4. **`Renderer`** — recursively walks DOM nodes and dispatches them to element classes registered in `ElementRegistry`. Each element class matches against CSS classes and builds NISO STS XML.
+4. **`Converter`** — wraps the HTML source, normalizes whitespace, parses it with Nokogiri, and passes DOM nodes to the Renderer.
+
+5. **`Renderer`** — recursively walks DOM nodes and dispatches them to element classes registered in `ElementRegistry`. Each element class matches against CSS classes and builds NISO STS XML.
 
 ### Element system
 
@@ -43,11 +46,15 @@ Data flows through these classes in `lib/obp/access/`:
 
 ### Supporting classes
 
-- **`GrammarParser`** — extracts part-of-speech and gender from bold term markup.
+- **`GrammarParser`** — extracts part-of-speech and gender from bold term markup (POS markers `adj.`/`verb`, gender markers `m`/`f`/`n`, 〈bracketed〉 subject fields). Gender/POS only occur in non-English term entries (fr/de/ru); examples live in `spec/obp/access/grammar_parser_spec.rb`.
 - **`DomainExtractor`** — extracts subject-field domains from definition text.
 - **`InlineRenderer`** — renders inline HTML elements (links, xrefs, italic, bold, entailed terms) to STS XML.
 - **`Imager`** — downloads images from OBP. Uses `Parallel` for concurrent downloads.
 
+### Testing conventions
+
+- Captured OBP HTML fixtures live in `obp-output/` at the repo root (gitignored — download them via the CLI or a browser). Conversion specs read them through `Access.from_html` and **skip** when the fixture is absent, so the offline suite never touches the network.
+
 ## Key dependencies
 
 - **sts** — NISO STS gem for generating STS objects from XML

data/README.adoc

@@ -54,6 +54,27 @@ obp = Obp::Access.fetch("iso:std:iso:5598:ed-3:v1:en", languages: :all)
 obp.to_xml(pretty: true) # => NISO STS XML with all available language langSets
 ----
 
+==== Already-downloaded HTML
+
+When the OBP page was fetched out of band (e.g. through a browser or
+waffle-punch), build an Access instance from the raw HTML fragment and
+convert it without any further network calls:
+
+[source,ruby]
+----
+obp = Obp::Access.from_html(
+  urn:     "iso:std:iso:80000-12:ed-2:v2:en",
+  html:    File.read("iso-80000-12-en.html"),
+  caption: "ISO 80000-12:2019",
+  titles:  { "en" => "Quantities and units — Part 12: Solid state physics" },
+)
+obp.to_xml(pretty: true) # => NISO STS XML
+obp.to_terms             # => YAML string of table-carried terms
+----
+
+`caption` is used to build the STS metadata (std-ref, copyright year); it
+should match the document reference. `titles` is optional.
+
 ==== CLI
 
 Fetch a single document (English only):
@@ -86,6 +107,117 @@ The output is NISO STS XML with TBX-Basic terminology markup:
 * Domains are extracted as `<tbx:subjectField>`
 * Deprecated terms use `<tbx:normativeAuthorization value="deprecatedTerm"/>`
 
+=== Tables and terms as YAML
+
+Besides STS XML, the same preview HTML can be read as YAML table data.
+ISO standards that carry terminology in tables rather than TBX term
+sections (the ISO 80000 quantity tables, "list of equivalent terms"
+tables) become machine-readable through two views:
+
+[source,ruby]
+----
+obp = Obp::Access.fetch("iso:std:iso:80000-12:ed-2:v2:en")
+obp.to_tables # => YAML string: every table in the document
+obp.to_terms  # => YAML string: term entries from term-carrying tables
+----
+
+Both reuse the already-fetched preview HTML, so no extra OBP request is
+made. A document without tables yields an empty YAML array (`--- []`).
+
+==== Generic tables (`to_tables`)
+
+`Obp::Access::TableMapper` maps every table-carrying node —
+`div.sts-table-wrap` and `div.sts-array`, in document order — to plain
+hashes, arrays and strings:
+
+[source,yaml]
+----
+- id: iso_std_iso_80000-12_ed-2_v2_en_tab_1 # wrapper id, if present
+  section: '3'      # containing clause ("index"/"bibl"/... stay raw)
+  label: Table 1    # .sts-caption-label, if present
+  caption: Quantities and units used in condensed matter physics
+  header:
+  - - text: Item No.
+    - text: Quantity
+      colspan: 3    # colspan/rowspan only when greater than 1
+    - text: Unit
+    - text: Remarks
+  rows:
+  - - text: 12-1.1
+    - text: lattice vector
+    - text: R
+    - text: translation vector that maps the crystal lattice on itself
+    - text: m
+    - text: The non-SI unit ångström (Å) is widely used ...
+----
+
+Cell text is plain stripped text: OBP `sts-unknown-element` placeholder
+spans are removed, and `<br>` / `div.sts-p` boundaries become spaces so
+multi-paragraph cells do not glue words together.
+
+==== Term entries (`to_terms`)
+
+`Obp::Access::TableTermExtractor` consumes the generic table model (not
+raw HTML) and extracts entries from term-carrying tables. Recognition
+rules, first match wins per table:
+
+. *Quantity/item tables* (ISO 80000 family): at least 4 columns, the
+  table sits in a numbered clause, and a majority of body rows start
+  with an item number (`12-1.1`, `4-1`). Column roles are resolved from
+  the joined header text — this handles the two-row colspan headers in
+  both English (Item No. / Quantity / Unit / Remarks) and French
+  (N° / Grandeur / Unité / Remarques) — falling back to the ISO 80000
+  column order item, designation, symbol, definition, unit, remarks.
+. *Equivalent-terms tables*: a header row naming languages in at least
+  2 columns. One entry per row, with `designations` keyed by downcased
+  language name; rows with a single designation (letter dividers) are
+  skipped.
+. Anything else is not a term table and yields no entries.
+
+[source,yaml]
+----
+- id: 12-1.1
+  designation: lattice vector
+  definition: translation vector that maps the crystal lattice on itself
+  symbol: R
+  unit: m
+  remarks: The non-SI unit ångström (Å) is widely used ...
+  source:
+    table: iso_std_iso_80000-12_ed-2_v2_en_tab_1
+    section: '3'
+- id: '2'
+  designations:
+    english: absorption, atmospheric
+    francais: absorption atmosphérique
+    deutsch: atmosphärische Absorption
+  source:
+    section: '1.1'
+----
+
+Only non-empty fields are emitted (`id` and `designation` are always
+present); duplicate item numbers within one table keep the first row.
+For equivalent-terms tables the entry `id` is the row's first cell when
+it looks like an item number, else the 1-based row index.
+
+==== Known limitations
+
+* Column mapping is header-text and position based; exotic header
+  layouts (rowspans in `thead`, role columns in unusual order) are not
+  resolved.
+* Quantity tables are recognized only in numbered clauses and only when
+  a strict majority of rows start with an item number; continuation
+  rows (blank item number) are skipped rather than merged into the
+  previous entry.
+* Item numbers must match `\d+-\d+(\.\d+)?` (U+2011 non-breaking hyphen
+  is normalized to `-`); rows printed differently in the source, such
+  as the `3.10.2` typo in ISO 80000-3, are skipped.
+* Cell text is flattened: subscripts/superscripts, inline formulas and
+  images lose their markup (`a1` for a₁), and French gender markers stay
+  glued to designations (`vecteur du réseau, m`).
+* Equivalent-terms designations are keyed by the downcased header text
+  as printed (`francais` in ISO 5843-6); mojibake headers (e.g.
+  `PyCCKMM` for Russian) are not recognized as languages.
+
 == Credits
 
 This gem is developed, maintained and funded by

data/lib/obp/access/element_registry.rb

@@ -11,8 +11,10 @@ module Obp
           @elements ||= []
         end
 
+        # Flattened unique class names across all registered elements, so
+        # callers can test membership against individual node classes.
         def css_classes
-          @css_classes ||= elements.filter_map(&:classes).uniq
+          @css_classes ||= elements.filter_map(&:classes).flatten.uniq
         end
       end
     end

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

@@ -17,12 +17,17 @@ module Obp
             nil
           end
 
+          # Subset match: OBP varies class order and adds marker classes
+          # (e.g. "commentable"), so a node matches when it carries at
+          # least the registered classes, regardless of order or extras.
           def match_node?
-            node.classes == self.class.classes
+            (self.class.classes - node.classes).empty?
           end
 
           def render(target:)
-            effective_target = insertion_target || target
+            # Top-level nodes without their own insertion target (e.g. a
+            # floating sts-p between sections) default to the body.
+            effective_target = insertion_target || target || "body"
             effective_target = "#{effective_target}#{path_suffix}" if path_suffix
             document.at(effective_target).public_send(insert_method, to_xml)
           end
@@ -42,7 +47,7 @@ module Obp
           end
 
           def id
-            @id ||= node.attr("id").split("_").last
+            @id ||= node.attr("id")&.split("_")&.last
           end
 
           def to_xml

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

@@ -0,0 +1,53 @@
+module Obp
+  class Access
+    class Renderer
+      class Elements
+        class DispFormula < Base
+          def self.classes
+            %w[sts-disp-formula-panel]
+          end
+
+          private
+
+          def content
+            Nokogiri::XML::Builder.new do |xml|
+              xml.public_send(:"disp-formula") do
+                xml.label label if label
+                if math
+                  xml << math.to_xml
+                elsif graphic_path
+                  xml.graphic("xlink:href": graphic_path)
+                end
+              end
+            end
+          end
+
+          def label
+            text = node.at_css(".sts-disp-formula-label")&.text&.strip
+            text unless text&.empty?
+          end
+
+          def math
+            @math ||= node.at_css("math")
+          end
+
+          # OBP serves formula images from its own graphics store, which
+          # Imager does not download; fall back to the original src.
+          def graphic_path
+            @graphic_path ||= begin
+              img = node.at_css("img")
+              img && (stored_image_path(img) || img.attr("src"))
+            end
+          end
+
+          def stored_image_path(img)
+            images = metas["images"]
+            images[img.attr("src")] if images.is_a?(Hash)
+          end
+        end
+      end
+    end
+  end
+end
+
+Obp::Access::ElementRegistry.register(Obp::Access::Renderer::Elements::DispFormula)

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

@@ -0,0 +1,54 @@
+module Obp
+  class Access
+    class Renderer
+      class Elements
+        # OBP emits page footnotes as a trailing "sts-footnotes" container
+        # holding one "sts-fn" div per note, each text prefixed with the
+        # note number.
+        class Footnotes < Base
+          def self.classes
+            %w[sts-footnotes]
+          end
+
+          private
+
+          def insertion_target
+            "back"
+          end
+
+          def content
+            Nokogiri::XML::Builder.new do |xml|
+              xml.public_send(:"fn-group") do
+                node.css("div.sts-fn").each { |note| render_fn(xml, note) }
+              end
+            end
+          end
+
+          def render_fn(xml, note)
+            id = fn_id(note)
+            xml.fn(id: "fn_#{id}") do
+              xml.label id
+              xml.p fn_text(note)
+            end
+          end
+
+          def fn_id(note)
+            note.attr("id")&.split("_")&.last || note.object_id.to_s
+          end
+
+          def fn_text(note)
+            div = note.at_css("div")
+            if div
+              div.text.strip.sub(/\A\d+\s*/,
+                                 "")
+            else
+              note.text.strip.sub(/\A\d+\s*/, "")
+            end
+          end
+        end
+      end
+    end
+  end
+end
+
+Obp::Access::ElementRegistry.register(Obp::Access::Renderer::Elements::Footnotes)

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

@@ -0,0 +1,28 @@
+module Obp
+  class Access
+    class Renderer
+      class Elements
+        # Renders the example label; the content div.sts-p children are
+        # rendered by Paragraph when the renderer recurses into them.
+        class NonNormativeExample < Base
+          def self.classes
+            %w[sts-non-normative-example]
+          end
+
+          private
+
+          def content
+            Nokogiri::XML::Builder.new do |xml|
+              xml.public_send(:"non-normative-example") do
+                label_node = node.at_css(".sts-non-normative-example-label")
+                xml.label label_node.text if label_node
+              end
+            end
+          end
+        end
+      end
+    end
+  end
+end
+
+Obp::Access::ElementRegistry.register(Obp::Access::Renderer::Elements::NonNormativeExample)

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

@@ -0,0 +1,25 @@
+module Obp
+  class Access
+    class Renderer
+      class Elements
+        # OBP replaces paywalled sections with this placeholder ("Only
+        # informative sections of standards are publicly available...").
+        # Skip it explicitly: render nothing and halt recursion, so the
+        # placeholder text never leaks into the output.
+        class ProtectedContentNote < Base
+          def self.classes
+            %w[sts-protected-content-note]
+          end
+
+          # Accepts (and ignores) the render target; the nil return tells
+          # the renderer to halt recursion into this subtree.
+          def render(*)
+            nil
+          end
+        end
+      end
+    end
+  end
+end
+
+Obp::Access::ElementRegistry.register(Obp::Access::Renderer::Elements::ProtectedContentNote)

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

@@ -42,7 +42,7 @@ module Obp
           def std_meta_content(xml)
             render_titles(xml)
             xml.public_send(:"proj-id", ref_undated)
-            xml.public_send(:"release-version", doc_type)
+            xml.public_send(:"release-version", urn.doc_type)
             render_std_ident(xml)
             xml.public_send(:"content-language", metas["language"])
             xml.public_send(:"std-ref", ref_dated, type: "dated")
@@ -55,10 +55,10 @@ module Obp
           def render_std_ident(xml)
             xml.public_send(:"std-ident") do
               xml.originator holder
-              xml.public_send(:"doc-type", doc_type)
-              xml.public_send(:"doc-number", urn_parts[3])
-              xml.edition urn_parts[4].delete_prefix("ed-")
-              xml.version urn_parts[5].delete_prefix("v")
+              xml.public_send(:"doc-type", urn.doc_type)
+              xml.public_send(:"doc-number", urn.doc_number)
+              xml.edition urn.edition
+              xml.version urn.version
             end
           end
 
@@ -85,35 +85,27 @@ module Obp
           end
 
           def holder
-            metas["caption"].split.first
+            caption&.split(/[[:space:]]/)&.first || urn.originator.upcase
           end
 
           def ref
-            metas["caption"]
+            caption || urn.to_s
           end
 
           def ref_dated
-            metas["caption"].gsub(/\(.*?\)/, "")
+            caption&.gsub(/\([^()]*\)/, "") || ref
           end
 
           def ref_undated
-            @ref_undated ||= metas["caption"].split(":").first
+            @ref_undated ||= caption&.split(":")&.first || urn.doc_number
           end
 
           def copyright_year
-            metas["caption"][/:(\d{4})/, 1]
+            caption&.[](/:(\d{4})/, 1)
           end
 
-          def doc_type
-            case urn_parts[3]
-            when "ts" then "TS"
-            when "tr" then "TR"
-            else "IS"
-            end
-          end
-
-          def urn_parts
-            @urn_parts ||= urn.raw.split(":")
+          def caption
+            metas["caption"]
           end
         end
       end