relaton 3.0.0.pre.alpha.4 → 3.0.0.pre.alpha.5

data/lib/relaton/jis/scraper.rb

@@ -22,7 +22,7 @@ module Relaton
       end
 
       def fetch # rubocop:disable Metrics/MethodLength
-        @doc = @agent.get(@url).at "//div[@id='main']/section"
+        @doc = @agent.get(@url).at_xpath "//div[@id='main']/section"
         contributors = fetch_contributor
         eg_contributor = fetch_editorialgroup_contributor
         contributors << eg_contributor if eg_contributor
@@ -33,7 +33,7 @@ module Relaton
 
       def fetch_title
         result = { "ja" => "Jpan", "en" => "Latn" }.map.with_index do |(lang, script), i|
-          content = @doc.at("./h2/text()[#{i + 2}]").text.strip
+          content = @doc.at_xpath("./h2/text()[#{i + 2}]").text.strip
           Bib::Title.new content: content, language: lang, script: script
         end
         @errors[:title] &&= result.empty?
@@ -84,12 +84,12 @@ module Relaton
       end
 
       def document_id
-        @document_id ||= @doc.at("./h2/text()[1]")&.text&.strip
+        @document_id ||= @doc.at_xpath("./h2/text()[1]")&.text&.strip
       end
 
       def fetch_date
         result = DATETYPES.each_with_object([]) do |(key, type), a|
-          node = @doc.at("./div/div/div/p/text()[contains(.,'#{key}')]")
+          node = @doc.at_xpath("./div/div/div/p/text()[contains(.,'#{key}')]")
           next unless node
 
           at = node.text.match(/\d{4}-\d{2}-\d{2}/).to_s
@@ -116,7 +116,7 @@ module Relaton
       def langs_scripts # rubocop:disable Metrics/MethodLength
         @langs_scripts ||= begin
           result = LANGS.each_with_object([]) do |(key, lang), a|
-            l = @doc.at(
+            l = @doc.at_xpath(
               "./div/div/div[@class='blockContentFile']/div/div/p[1]" \
               "/span[contains(.,'#{key}')]/following-sibling::span",
             )
@@ -132,7 +132,7 @@ module Relaton
       def fetch_status
         xpath = "./div/div/div/p/text()[contains(.,'状態')]" \
                 "/following-sibling::span"
-        st = @doc.at(xpath)
+        st = @doc.at_xpath(xpath)
         status_val = STATUSES[st&.text&.strip]
         @errors[:status] &&= status_val.nil?
         return unless status_val
@@ -155,7 +155,7 @@ module Relaton
       end
 
       def fetch_ics
-        td = @doc.at("./table/tr[th[.='ICS']]/td")
+        td = @doc.at_xpath("./table/tr[th[.='ICS']]/td")
         @errors[:ics] &&= td.nil?
         return [] unless td
 
@@ -194,7 +194,7 @@ module Relaton
       end
 
       def fetch_editorialgroup_contributor # rubocop:disable Metrics/MethodLength
-        node = @doc.at("./table/tr[th[.='原案作成団体']]/td")
+        node = @doc.at_xpath("./table/tr[th[.='原案作成団体']]/td")
         @errors[:editorialgroup] &&= node.nil?
         return unless node
 

data/lib/relaton/oasis/browser_agent.rb

@@ -1,5 +1,5 @@
 require "ferrum"
-require "nokogiri"
+require "moxml"
 
 module Relaton
   module Oasis
@@ -42,7 +42,7 @@ module Relaton
       def get(url)
         @browser.go_to(url)
         wait_for_challenge
-        Nokogiri::HTML(@browser.body)
+        Moxml.new.parse_html(@browser.body)
       end
 
       # HTTP status code of the most recent navigation's main resource,

data/lib/relaton/oasis/data_parser.rb

@@ -7,7 +7,7 @@ module Relaton
       #
       # Initialize parser.
       #
-      # @param [Nokogiri::HTML::Element] node document node
+      # @param [Moxml::Element] node document node
       #
       def initialize(node, errors = {}, agent: nil)
         @node = node
@@ -16,14 +16,14 @@ module Relaton
       end
 
       def title
-        @title ||= @node.at("./summary/div/h2").text
+        @title ||= @node.at_xpath("./summary/div/h2").text
       end
 
       def text
         xpath = "./div/div/div[contains(@class, " \
                 "'standard__grid--cite-as')]" \
                 "/p[em or i or a or span]"
-        @text ||= @node.at(xpath)&.text&.strip
+        @text ||= @node.at_xpath(xpath)&.text&.strip
       end
 
       #
@@ -144,7 +144,7 @@ module Relaton
         xpath = "./div/div/div[contains(@class, " \
                 "'standard__grid--cite-as')]" \
                 "/p[strong or span/strong]/a"
-        @link_node ||= @node.at(xpath)
+        @link_node ||= @node.at_xpath(xpath)
       end
 
       #
@@ -220,7 +220,7 @@ module Relaton
         parts = document_part_refs
         result = case parts.size
                  when 0
-                   txt = @node.at("./summary/div/h2").text
+                   txt = @node.at_xpath("./summary/div/h2").text
                    parse_spec title_to_docid(txt)
                  when 1 then parse_part parse_spec(parts[0])
                  else parts_to_docid parts

data/lib/relaton/oasis/data_parser_utils.rb

@@ -83,7 +83,7 @@ module Relaton
       # @param [#get] agent HTTP client responding to #get(url)
       # @param [Integer] retries number of retries
       #
-      # @return [Nokogiri::HTML::Document, Mechanize::Page, nil] page or nil
+      # @return [Moxml::Document, Mechanize::Page, nil] page or nil
       #
       def retry_page(url, agent, retries = 3)
         sleep 1 # to avoid 429 error
@@ -156,7 +156,7 @@ module Relaton
         href = email[:href]
         if href.start_with?("mailto:")
           [href.split(":")[1]]
-        elsif (cf_email = email.at(".//span[@data-cfemail]"))
+        elsif (cf_email = email.at_xpath(".//span[@data-cfemail]"))
           decoded = decode_cf_email(cf_email["data-cfemail"])
           return [] if decoded.empty?
 

data/lib/relaton/oasis/data_part_parser.rb

@@ -7,7 +7,7 @@ module Relaton
       #
       # Initialize parser.
       #
-      # @param [Nokogiri::HTML::Element] node document node
+      # @param [Moxml::Element] node document node
       #
       def initialize(node, errors = {}, agent: nil)
         @node = node
@@ -20,7 +20,7 @@ module Relaton
 
         sibling_xpath = "./strong/following-sibling::text()" \
                         "|./span[strong]/following-sibling::text()"
-        if @node.at(sibling_xpath)
+        if @node.at_xpath(sibling_xpath)
           nodes_xpath = "./strong/following-sibling::node()" \
                         "|./span[strong]/following-sibling::node()"
           @text = @node.xpath(nodes_xpath).text.strip
@@ -34,7 +34,7 @@ module Relaton
 
         xpath = "./span[@class='citationTitle' " \
                 "or @class='citeTitle']|./em|./i"
-        t = @node.at(xpath)
+        t = @node.at_xpath(xpath)
         @title = if t
                    t.text
                  else
@@ -83,7 +83,7 @@ module Relaton
       # @return [String] document number
       #
       def parse_docnumber
-        ref = @node.at("./span/strong|./strong|./b/span")
+        ref = @node.at_xpath("./span/strong|./strong|./b/span")
         num = ref.text.match(/[^\[\]]+/).to_s
         id = parse_errata(num)
         # some part refs need "Pt" to distinguish from root doc
@@ -183,7 +183,7 @@ module Relaton
       # @return [Array<Bib::Relation>] document relations
       #
       def parse_relation
-        parser = DataParser.new(@node.at("./ancestor::details"), @errors, agent: @agent)
+        parser = DataParser.new(@node.at_xpath("./ancestor::details"), @errors, agent: @agent)
         fref = parser.parse_docid[0].content
         bib = ItemData.new(formattedref: Bib::Formattedref.new(content: fref))
         result = [Bib::Relation.new(type: "partOf", bibitem: bib)]
@@ -221,7 +221,7 @@ module Relaton
       end
 
       def link_node
-        @link_node = @node.at("./a|./following-sibling::p[1]/a")
+        @link_node = @node.at_xpath("./a|./following-sibling::p[1]/a")
       end
 
       #
@@ -230,7 +230,7 @@ module Relaton
       # @return [Array<String>] technology areas
       #
       def parse_technology_area
-        result = super(@node.at("./ancestor::details"))
+        result = super(@node.at_xpath("./ancestor::details"))
         @errors[:part_technology_area] &&= result.empty?
         result
       end

data/lib/relaton/ogc/processor.rb

@@ -21,6 +21,13 @@ module Relaton
         Bibliography.get(code, date, opts)
       end
 
+      # The `year` argument filters by publication year, but an OGC pubid's
+      # `year` is the year in the document number (`19` in `OGC 19-025r1`),
+      # so it cannot be folded into the key: such a query is not cached.
+      def cache_key(ref, year, opts)
+        year ? nil : super
+      end
+
       # @param source [String]
       # @param opts [Hash]
       def fetch_data(_source, opts)

data/lib/relaton/oiml/processor.rb

@@ -8,6 +8,7 @@ module Relaton
       def initialize
         @short = :relaton_oiml
         @prefix = "OIML"
+        @pubid_identifier = :Oiml # Db cache key
         @defaultprefix = %r{^OIML\s}
         @idtype = "OIML"
       end

data/lib/relaton/omg/scraper.rb

@@ -63,7 +63,7 @@ module Relaton
       end
 
       def fetch_title
-        content = @doc.at('//dt[.="Title:"]/following-sibling::dd').text
+        content = @doc.at_xpath('//dt[.="Title:"]/following-sibling::dd').text
         content += ": #{@part}" if @part
         [Bib::Title.new(type: "main", content: content, language: "en", script: "Latn")]
       end
@@ -76,7 +76,7 @@ module Relaton
       end
 
       def fetch_abstract
-        content = @doc.at('//section[@id="document-metadata"]/div/div/p').text
+        content = @doc.at_xpath('//section[@id="document-metadata"]/div/div/p').text
         [Bib::Abstract.new(content: content, language: "en", script: "Latn")]
       end
 
@@ -85,7 +85,7 @@ module Relaton
       end
 
       def doc_version
-        @doc_version ||= @doc.at('//dt[.="Version:"]/following-sibling::dd/p/span').text
+        @doc_version ||= @doc.at_xpath('//dt[.="Version:"]/following-sibling::dd/p/span').text
       end
 
       def fetch_date
@@ -105,7 +105,7 @@ module Relaton
       #
       # @return [Date, nil]
       def jsonld_date
-        script = @doc.at('//script[@type="application/ld+json"]')
+        script = @doc.at_xpath('//script[@type="application/ld+json"]')
         return unless script
 
         node = JSON.parse(script.text).find { |e| e.is_a?(Hash) && e[LD_DATE] }
@@ -117,7 +117,7 @@ module Relaton
 
       # @return [Date, nil]
       def dd_date
-        text = @doc.at('//dt[.="Publication Date:"]/following-sibling::dd').text.strip
+        text = @doc.at_xpath('//dt[.="Publication Date:"]/following-sibling::dd').text.strip
         ::Date.parse text
       rescue ::Date::Error
         Util.warn "Cannot parse the publication date `#{text}`."
@@ -125,7 +125,7 @@ module Relaton
       end
 
       def fetch_status
-        status = @doc.at('//dt[.="Document Status:"]/following-sibling::dd')
+        status = @doc.at_xpath('//dt[.="Document Status:"]/following-sibling::dd')
         stage = status.text.strip.match(/\w+/).to_s
         Bib::Status.new(stage: Bib::Status::Stage.new(content: stage))
       end
@@ -135,12 +135,12 @@ module Relaton
 
         @links = []
         if @part
-          a = @doc.at("//a[@href='#{@url}/#{@part}/PDF']")
+          a = @doc.at_xpath("//a[@href='#{@url}/#{@part}/PDF']")
           @links << Bib::Uri.new(type: "src", content: a[:href]) if a
         else
-          a = @doc.at('//dt[.="This Document:"]/following-sibling::dd/a')
+          a = @doc.at_xpath('//dt[.="This Document:"]/following-sibling::dd/a')
           @links << Bib::Uri.new(type: "src", content: a[:href]) if a
-          pdf = @doc.at('//a[@class="download-document"]')
+          pdf = @doc.at_xpath('//a[@class="download-document"]')
           @links << Bib::Uri.new(type: "pdf", content: pdf[:href]) if pdf
         end
         @links
@@ -149,9 +149,9 @@ module Relaton
       def fetch_relation
         v = @doc.xpath('//h2[.="History"]/following-sibling::section/div/table/tbody/tr')
         v.reduce([]) do |mem, row|
-          ver = row.at("td").text
+          ver = row.at_xpath("td").text
           unless ver == doc_version
-            acronym = row.at("td[3]/a")[:href].split("/")[4]
+            acronym = row.at_xpath("td[3]/a")[:href].split("/")[4]
             id = render_id(acronym, ver)
             docid = Docidentifier.new(content: id, type: "OMG")
             bibitem = Bib::ItemBase.new(formattedref: Bib::Formattedref.new(content: id), docidentifier: [docid])

data/lib/relaton/omg.rb

@@ -1,4 +1,4 @@
-require "nokogiri"
+require "moxml"
 require "relaton/bib"
 require_relative "version"
 require_relative "omg/util"

data/lib/relaton/plateau/processor.rb

@@ -8,6 +8,7 @@ module Relaton
       def initialize # rubocop:disable Lint/MissingSuper
         @short = :relaton_plateau
         @prefix = "PLATEAU"
+        @pubid_identifier = :Plateau # Db cache key
         @defaultprefix = /^PLATEAU\s/
         @idtype = "PLATEAU"
         @datasets = %w[plateau-handbooks plateau-technical-reports]

data/lib/relaton/un/bibliography.rb

@@ -15,25 +15,36 @@ module Relaton
                 "Could not access #{HitCollection::API_BASE}: #{e.message}"
         end
 
-        # @param ref [String] document reference
+        # @param ref [String, Pubid::Un::Identifier] document reference
         # @param year [String, NilClass]
         # @param opts [Hash] options
         # @return [Relaton::Bib::ItemData]
         def get(ref, _year = nil, _opts = {})
-          Util.info "Fetching from documents.un.org ...", key: ref
-          /^(?:UN\s)?(?<code>.*)/ =~ ref
-          result = isobib_search_filter(code)
-          if result
-            Util.info "Found: `#{result.item.docidentifier[0].content}`", key: ref
-            result.item
-          else
-            Util.info "Not found.", key: ref
-            nil
+          key = ref.to_s
+          Util.info "Fetching from documents.un.org ...", key: key
+          item = isobib_search_filter(document_symbol(ref))&.item
+          unless item
+            Util.info "Not found.", key: key
+            return
           end
+
+          Util.info "Found: `#{item.docidentifier[0].content}`", key: key
+          item
         end
 
         private
 
+        # The UN document symbol to search for. A parsed pubid renders it
+        # (`TRADE/CEFACT/2004/32`); a String may start with a `UN ` token.
+        #
+        # @param ref [String, Pubid::Un::Identifier]
+        # @return [String]
+        def document_symbol(ref)
+          return ref.to_s unless ref.is_a?(String)
+
+          ref[/^(?:UN\s)?(.*)/, 1]
+        end
+
         # Search for hits.
         #
         # @param code [String] reference without correction

data/lib/relaton/un/processor.rb

@@ -10,6 +10,7 @@ module Relaton
       def initialize
         @short = :relaton_un
         @prefix = "UN"
+        @pubid_identifier = :Un # Db cache key
         @defaultprefix = %r{^UN\s}
         @idtype = "UN"
       end

data/lib/relaton/version.rb

@@ -1,3 +1,3 @@
 module Relaton
-  VERSION = "3.0.0.pre.alpha.4".freeze
+  VERSION = "3.0.0.pre.alpha.5".freeze
 end

data/lib/relaton/w3c/processor.rb

@@ -8,6 +8,7 @@ module Relaton
       def initialize # rubocop:disable Lint/MissingSuper
         @short = :relaton_w3c
         @prefix = "W3C"
+        @pubid_identifier = :W3c # Db cache key
         @defaultprefix = %r{^W3C\s}
         @idtype = "W3C"
         @datasets = %w[w3c-api]

data/lib/relaton.rb

@@ -5,6 +5,18 @@
 # `require "relaton/<flavor>"`, loading that flavor's code on demand rather than
 # at `require "relaton"`. When adding a flavor, add an autoload line here.
 require "relaton/version"
+require "moxml"
+
+# YAML through yeptris (Psych-compatible drop-in; stdlib Psych is kept
+# as Yeptris::Psych::ORIGINAL). Must load before any YAML/Psych use.
+# yeptris 0.5 moved the exclusive drop-in rebind to yeptris/psych/drop_in
+# — plain yeptris/psych only defines the namespace and leaves stdlib
+# Psych in place (yeptris-ruby#95, bug 3).
+# Load stdlib Psych first: the drop-in keeps it as Yeptris::Psych::ORIGINAL,
+# and a later plain require "psych" against the rebound constant is a
+# superclass mismatch (yeptris-ruby#95, bug 3 follow-on).
+require "psych"
+require "yeptris/psych/drop_in"
 
 module Relaton
   autoload :Logger, "relaton/logger"
@@ -46,6 +58,7 @@ module Relaton
   autoload :Plateau, "relaton/plateau"
   autoload :Doi, "relaton/doi"
   autoload :Sdo, "relaton/sdo"
+  autoload :Cloud, "relaton/cloud"
 
   # Global PubID prefix register (relaton-db#103). Maps an SDO document-ID
   # prefix to the flavor module(s) that own it. Conflicting prefixes (e.g.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton
 version: !ruby/object:Gem::Version
-  version: 3.0.0.pre.alpha.4
+  version: 3.0.0.pre.alpha.5
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-09-25 00:00:00.000000000 Z
+date: 2026-09-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -302,14 +302,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 0.8.76
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 0.8.76
+- !ruby/object:Gem::Dependency
+  name: lutaml-store
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.2
 - !ruby/object:Gem::Dependency
   name: mechanize
   requirement: !ruby/object:Gem::Requirement
@@ -353,19 +367,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 0.3.4
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: moxml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0.5'
+- !ruby/object:Gem::Dependency
+  name: leptris
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: 1.9.80
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '1.16'
+        version: 1.9.80
 - !ruby/object:Gem::Dependency
   name: parallel
   requirement: !ruby/object:Gem::Requirement
@@ -395,33 +423,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 2.0.0
 - !ruby/object:Gem::Dependency
-  name: psych
+  name: pubid
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.2.0
+        version: 2.0.0.pre.alpha.13
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.2.0
+        version: 2.0.0.pre.alpha.13
 - !ruby/object:Gem::Dependency
-  name: pubid
+  name: yeptris
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0.pre.alpha.11
+        version: '0.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.0.pre.alpha.11
+        version: '0.4'
 - !ruby/object:Gem::Dependency
   name: rfcxml
   requirement: !ruby/object:Gem::Requirement
@@ -523,6 +551,9 @@ files:
 - lib/relaton/bib/converter/bibxml/from_rfcxml_referencegroup.rb
 - lib/relaton/bib/converter/bibxml/to_rfcxml.rb
 - lib/relaton/bib/converter/bibxml/to_rfcxml_referencegroup.rb
+- lib/relaton/bib/converter/csl.rb
+- lib/relaton/bib/converter/ris.rb
+- lib/relaton/bib/converter/titles.rb
 - lib/relaton/bib/hash_parser_v1.rb
 - lib/relaton/bib/item_data.rb
 - lib/relaton/bib/model/abstract.rb
@@ -676,6 +707,7 @@ files:
 - lib/relaton/cie/processor.rb
 - lib/relaton/cie/scrapper.rb
 - lib/relaton/cie/util.rb
+- lib/relaton/cloud.rb
 - lib/relaton/core.rb
 - lib/relaton/core/array_wrapper.rb
 - lib/relaton/core/data_fetcher.rb
@@ -690,6 +722,7 @@ files:
 - lib/relaton/core/workers_pool.rb
 - lib/relaton/db.rb
 - lib/relaton/db/cache.rb
+- lib/relaton/db/cache_entry.rb
 - lib/relaton/db/config.rb
 - lib/relaton/db/registry.rb
 - lib/relaton/db/util.rb
@@ -945,7 +978,6 @@ files:
 - lib/relaton/itu/model/recommendation_status.rb
 - lib/relaton/itu/model/structured_identifier.rb
 - lib/relaton/itu/processor.rb
-- lib/relaton/itu/pubid.rb
 - lib/relaton/itu/radio_regulations_parser.rb
 - lib/relaton/itu/recommendation_fields.rb
 - lib/relaton/itu/recommendation_parser.rb