relaton-itu 1.20.1 → 1.20.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5f782e5e67be5f75336a106dd6e2366aabf9085391d20f0e0e0424d7965e2b7f
-  data.tar.gz: 3491eda42b19b30bdbc7568f8a8e436c6d64bfcef80298ff6ca57c50e93737b8
+  metadata.gz: f70f91da524595847c16b4a8cb46dc7379a254822a84b03034e9b4965560ff4a
+  data.tar.gz: eb69591d51a38a1ad4c99f5914f2fd7be27abaad712947ea04a603939fe65196
 SHA512:
-  metadata.gz: 48987e9207d2a28778de5442e53ac2cba35481a219791aba02f119ed2048ec3018effffbea90d825cb3702c4e3c04285e649264542a6686163d046e52a528957
-  data.tar.gz: 2ece9eb73b4dbdb478d2c54d635c76cd8b11f54a59357aed2a8227a7fb69a5cb5d5cf7eaefcb4b0fa6a907fb93b95afcf80e0b950e44d533fb86456cc7db9bda
+  metadata.gz: 0d7300e181010d2bdd2829a0a888a0db59bd3c61448e09d840ab76f3a5c24b17700c5ea6ae4598e1aebfba82f173c3a619ad9e37e9581e26d636db601d178d99
+  data.tar.gz: b82909697c98ac580e0eaf13e1c0f0652365fb08f2951b8a86ffc7c972959703c916596b5f210624e6ec7945900502b63ac52f7ae516f4be0420fa79065ead8f

data/Gemfile

@@ -13,3 +13,7 @@ gem "ruby-jing"
 gem "simplecov"
 gem "vcr"
 gem "webmock"
+
+group :development do
+  gem 'pry'
+end

data/lib/relaton_itu/hit_collection.rb

@@ -45,6 +45,9 @@ module RelatonItu
       data = { json: params.to_json }
       resp = agent.post url, data
       @array = hits JSON.parse(resp.body)
+    rescue Mechanize::ResponseCodeError, SocketError, Timeout::Error, Errno::ECONNRESET,
+            EOFError, Net::ProtocolError, OpenSSL::SSL::SSLError => e
+      raise RelatonBib::RequestError, "Could not access #{url}: #{e.message}"
     end
 
     def request_document # rubocop:todo Metrics/MethodLength, Metrics/AbcSize

data/lib/relaton_itu/radio_regulations_parser.rb

@@ -0,0 +1,66 @@
+module RelatonItu
+  class RadioRegulationsParser
+    include Relaton::Core::ArrayWrapper
+
+    ROMAN_MONTHS = %w[I II III IV V VI VII VIII IX X XI XII].freeze
+
+    def initialize(hit)
+      @hit = hit
+    end
+
+    def doc
+      @doc ||= hit.hit_collection.agent.get doc_url
+    rescue Mechanize::ResponseCodeError, SocketError, Timeout::Error, Errno::ECONNRESET,
+            EOFError, Net::ProtocolError, OpenSSL::SSL::SSLError => e
+      raise RelatonBib::RequestError, "Could not access #{url}: #{e.message}"
+    end
+
+    def doc_url
+      CGI.unescape(hit.hit[:url]).split("dest=").last
+    end
+
+    def fetch_edition = nil
+    def fetch_status = nil
+    def fetch_workgroup = nil
+    def fetch_abstract = []
+    def fetch_relations = []
+
+    def fetch_titles
+      title = doc.at("//title")&.text&.strip
+      return [] if title.nil? || title.empty?
+
+      RelatonBib::TypedTitleString.from_string title, "en", "Latn"
+    end
+
+    def fetch_dates
+      array(doc_date).map { |on| { type: "published", on: on } }
+    end
+
+    def doc_date
+      return @doc_date if defined? @doc_date
+
+      date_str = doc.at("//td[@class='title']/text()")&.text&.slice(/(?<=Year:\s)(?:\d{1,2}\.\w+\.)?\d{4}/)
+      @doc_date = date_str ? roman_to_arabic(date_str) : nil
+    end
+
+    def fetch_link
+      [RelatonBib::TypedUri.new(type: "src", content: doc_url)]
+    end
+
+    private
+
+    attr_reader :hit
+
+    # Convert roman month number in string date to arabic number
+    # @param date [String]
+    # @return [String]
+    def roman_to_arabic(date)
+      %r{(?<rmonth>[IVX]+)} =~ date
+      if ROMAN_MONTHS.index(rmonth)
+        month = ROMAN_MONTHS.index(rmonth) + 1
+        Date.parse(date.sub(%r{[IVX]+}, month.to_s)).to_s
+      else date
+      end
+    end
+  end
+end

data/lib/relaton_itu/recommendation_parser.rb

@@ -0,0 +1,191 @@
+module RelatonItu
+  # Parse ITU Radio Regulations from XML to Relaton format.
+  class RecommendationParser
+    include Relaton::Core::ArrayWrapper
+
+    RECHDR = "https://www.itu.int/mws/api/recommendations/getRecHdrDetail?idrec=%{idrec}&lang=en".freeze
+    RECEDITIONS = "https://www.itu.int/mws/api/recommendations/getRecEditions?idrec=%{idrec}&lang=en".freeze
+    RECSUPPLEMENTS = "https://www.itu.int/mws/api/recommendations/getRecSupplements?idrec=%{idrec}&lang=en".freeze
+    IMPLGUIDES = "https://www.itu.int/mws/api/recommendations/getImplGuides?idrec=%{idrec}&lang=en".freeze
+
+    def initialize(hit, idrec, imp)
+      @hit = hit
+      @idrec = idrec
+      @imp = imp
+    end
+
+    def doc
+      @doc ||= begin
+        url = (imp ? IMPLGUIDES : RECHDR ) % { idrec: idrec }
+        resp = get_data url
+        imp ? resp.first : resp
+      end
+    end
+
+    # @return [Strign, nil]
+    def fetch_edition
+      self_edition.dig("Version")
+    end
+
+    # Fetch titles.
+    # @return [RelatonBib::TypedTitleStringCollection]
+    def fetch_titles
+      title = imp ? doc["imp_title_e"] : doc["rec_title"]
+      return [] if title.nil? || title.empty?
+
+      RelatonBib::TypedTitleString.from_string title, "en", "Latn"
+    end
+
+    # Fetch status.
+    # @return [RelatonBib::DocumentStatus, NilClass]
+    def fetch_status
+      inforce = imp ? imp_status : doc["status"]
+      return if inforce.nil? || inforce.empty?
+
+      status = inforce == "In force" ? "Published" : "Withdrawal"
+      RelatonBib::DocumentStatus.new(stage: status)
+    end
+
+    # Fetch dates
+    # @return [Array<Hash>]
+    def fetch_dates
+      array(doc_date).map { |on| { type: "published", on: on } }
+    end
+
+    # Fetch workgroup.
+    # @return [RelatonItu::EditorialGroup, NilClass]
+    def fetch_workgroup
+      group = itugroup(doc["sg"])
+      EditorialGroup.new(
+        bureau: hit.hit[:code].match(/(?<=-)./).to_s, group: group
+      )
+    end
+
+    # Fetch abstracts.
+    # @return [Array<Hash>]
+    def fetch_abstract
+      array(doc["summary"]).map do |content|
+        { content: content, language: "en", script: "Latn" }
+      end
+    end
+
+    # Fetch links.
+    # @return [Array<Hash>]
+    def fetch_link
+      link = imp ? doc["imp_dms_link"] : doc["handle_id"]
+      links = [{ type: "src", content: link }]
+      links << typed_link("pdf", doc["handle_id_pdf_link"]) if doc["handle_id_pdf_link"]
+      imp_word_link { |wlink| links << typed_link("word", wlink) }
+      links
+    end
+
+    def doc_date
+      return @doc_date if defined? @doc_date
+
+      date = imp ? doc["imp_approval_date"] : doc["approval_date"]
+      @doc_date = Date.parse(date).to_s rescue date
+    end
+
+    # Fetch relations.
+    # @return [Array<Hash>]
+    def fetch_relations
+      relations = []
+      editions.each do |ed|
+        next if ed["idrec"] == idrec
+
+        relations << create_relation("hasEdition", ed["title"], ed["rec_name"])
+      end
+
+      supplements.each { |supp| relations << create_relation("complementOf", supp["title_text"], supp["rec_name"]) }
+      relations
+    end
+
+    private
+
+    attr_reader :hit, :idrec, :imp
+
+    # Get data.
+    # @param url [String, nil]
+    # @return [Array<String, Nokogiri::HTML::Document>]
+    def get_data(url)
+      JSON.parse request_document(url).body
+    end
+
+    def request_document(url)
+      hit.hit_collection.agent.get url
+    rescue Mechanize::ResponseCodeError, SocketError, Timeout::Error, Errno::ECONNRESET,
+            EOFError, Net::ProtocolError, OpenSSL::SSL::SSLError => e
+      raise RelatonBib::RequestError, "Could not access #{url}: #{e.message}"
+    end
+
+    def editions
+      @editions ||= begin
+        url = RECEDITIONS % { idrec: idrec }
+        get_data(url) || []
+      end
+    end
+
+    def self_edition
+      @self_edition ||= editions.find { |ed| ed["idrec"] == idrec }
+    end
+
+    def imp_status
+      self_edition.dig("status")
+    end
+
+    # @param name [String]
+    # @return [RelatonItu::ItuGroup]
+    def itugroup(name) # rubocop:disable Metrics/MethodLength
+      return if name.nil? || name.empty?
+
+      if name.include? "Study Group"
+        type = "study-group"
+        acronym = "SG"
+      elsif name.include? "Telecommunication Standardization Advisory Group"
+        type = "tsag"
+        acronym = "TSAG"
+      else
+        type = "work-group"
+        acronym = "WG"
+      end
+      ItuGroup.new name: name, type: type, acronym: acronym
+    end
+
+    def imp_word_link
+      return unless doc["imp_dms_link"]
+      @doc_page ||= request_document(doc["imp_dms_link"])
+      wrd_elm = @doc_page.at("//font[contains(.,'Word')]/../..")
+      yield wrd_elm[:href] if block_given? && wrd_elm
+    end
+
+    def create_relation(type, title_text, id)
+      title = []
+      if title_text && !title.empty?
+        title << RelatonBib::TypedTitleString.new(content: title_text, language: "en", script: "Latn")
+      else
+        fref = RelatonBib::FormattedRef.new(content: id, language: "en", script: "Latn")
+      end
+
+      did = RelatonBib::DocumentIdentifier.new(id: id, type: "ITU", primary: true)
+      item = ItuBibliographicItem.new(title: title, formattedref: fref, docid: [did])
+      { type: "hasEdition", bibitem: item }
+    end
+
+    def supplements
+      @supplements ||= begin
+        if imp
+          []
+        else
+          url = RECSUPPLEMENTS % { idrec: idrec }
+          get_data(url) || []
+        end
+      end
+    end
+
+    # @param type [String]
+    # @param url [Nokogiri::XML::Element]
+    def typed_link(type, url)
+      { type: type, content: url }
+    end
+  end
+end

data/lib/relaton_itu/scrapper.rb

@@ -2,11 +2,13 @@
 
 require "nokogiri"
 require "net/http"
+require_relative "recommendation_parser"
+require_relative "radio_regulations_parser"
 
 module RelatonItu
   # Scrapper.
-  module Scrapper
-    ROMAN_MONTHS = %w[I II III IV V VI VII VIII IX X XI XII].freeze
+  class Scrapper
+    attr_reader :hit, :imp
 
     TYPES = {
       "ISO" => "international-standard",
@@ -23,302 +25,145 @@ module RelatonItu
       "Guide" => "guide",
     }.freeze
 
-    class << self
-      # Parse page.
-      # @param hit [RelatonItu::Hit]
-      # @return [Hash]
-      def parse_page(hit, imp: false) # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
-        doc = get_page hit
-        return unless doc.code == "200"
-
-        if imp
-          a = doc.at "//span[contains(@id, 'tab_ig_uc_rec')]/a"
-          return unless a
-
-          doc = get_page hit, a[:href].to_s
-        end
-
-        # Fetch edition.
-        edition = doc.at("//table/tr/td[contains(@style,'color: white')]/span[contains(@id, 'Label8')]/b")&.text
-        docid = fetch_docid(doc, hit)
-
-        ItuBibliographicItem.new(
-          id: fetch_id(docid),
-          fetched: Date.today.to_s,
-          type: "standard",
-          docid: docid,
-          edition: edition,
-          language: ["en"],
-          script: ["Latn"],
-          title: fetch_titles(doc),
-          doctype: DocumentType.new(type: hit.hit[:type]),
-          docstatus: fetch_status(doc),
-          ics: [], # fetch_ics(doc),
-          date: fetch_dates(doc),
-          contributor: fetch_contributors(hit.hit[:code]),
-          editorialgroup: fetch_workgroup(hit.hit[:code], doc),
-          abstract: fetch_abstract(doc, hit),
-          copyright: fetch_copyright(hit.hit[:code], doc),
-          link: fetch_link(doc),
-          relation: fetch_relations(doc),
-          place: ["Geneva"],
-        )
-      end
-
-      private
-
-      def fetch_id(docid)
-        docid.find(&:primary).id.gsub(/[.\s()\/-]/, "")
-      end
-
-      # Fetch abstracts.
-      # @param doc [Mechanize::Page]
-      # @param hit [RelatonItu::Hit]
-      # @return [Array<Hash>]
-      def fetch_abstract(doc, hit) # rubocop:disable Metrics/AbcSize,Metrics/MethodLength
-        abstract_url = doc.at '//table/tr/td[contains(@style,"color: white")]/span[contains(@id, "lbl_dms")]/div'
-        if abstract_url
-          url = abstract_url[:onclick].match(/https?[^']+/).to_s
-          rsp = hit.hit_collection.agent.get url
-          d = Nokogiri::HTML rsp.body.encode(undef: :replace, replace: "")
-          d.css("p.MsoNormal").text.gsub("\r\n", "").squeeze(" ").gsub("\u00a0", "")
-        elsif a = doc.at('//table/tr/td/span[contains(@class, "observation")]/text()')
-          a.text.strip
-        end => content
-        return [] unless content
-
-        [{
-          content: content,
-          language: "en",
-          script: "Latn",
-        }]
-      rescue Mechanize::ResponseCodeError => e
-        Util.error "HTTP Service Unavailable: #{e.message}"
-        []
-      end
-
-      # Get page.
-      # @param hit [RelatonItu::Hit]
-      # @param url [String, nil]
-      # @return [Array<String, Nokogiri::HTML::Document>]
-      def get_page(hit, url = nil)
-        uri = url || hit.hit[:url]
-        hit.hit_collection.agent.get uri
-      rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET,
-             EOFError, Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError,
-             Net::ProtocolError, OpenSSL::SSL::SSLError
-        raise RelatonBib::RequestError, "Could not access #{uri}"
-      end
-
-      # Fetch docid.
-      # @param doc [Mechanize::Page]
-      # @param hit [RelatonItu::Hit]
-      # @return [Hash]
-      def fetch_docid(doc, hit)
-        docids = hit.hit[:code].to_s.split(" | ").map { |c| createdocid(c) }
-        docids += parse_id(doc).map { |c| createdocid c.text } if docids.empty?
-        docids << createdocid(title) unless docids.any?
-        docids
-      end
-
-      def parse_id(doc)
-        doc.xpath(
-          "//span[@id='ctl00_content_main_uc_rec_main_info1_rpt_main_ctl00_lbl_rec']",
-          "//td[.='Identical standard:']/following-sibling::td",
-          "//div/table[1]/tr[4]/td/strong",
-        )
-      end
+    def initialize(hit, imp: false)
+      @hit = hit
+      @imp = imp
+    end
 
-      # @param text [String]
-      # @return [RelatonBib::DocumentIdentifier]
-      def createdocid(text) # rubocop:disable Metrics/MethodLength
-        # %r{
-        #   ^(?<code>(?:(?:ITU-\w|ISO/IEC)\s)?[^(:]*)
-        #   (?:\s\(V(?<version>\d+)\))?
-        #   (?:\s\((?:(?<_month>\d{2})/)?(?<_year>\d{4})\))?
-        #   (?::[^(]+\((?<buldate>\d{2}\.\w{1,4}\.\d{4})\))?
-        #   (?:\s(?<corr>(?:Amd|Cor)\.\s?\d+))?
-        #   # (\s\(((?<_cormonth>\d{2})\/)?(?<_coryear>\d{4})\))?
-        # }x =~ text.squeeze(" ")
-        # corr&.sub!(/\.\s?/, " ")
-        # id = [code.sub(/[[:space:]]$/, ""), corr].compact.join " "
-        # id += " (V#{version})" if version
-        # id += " - #{buldate}" if buldate
-        # type = id.match(%r{^\w+}).to_s
-        # type = "ITU" if type == "G"
-        if text.match?(/^(?:ISO|ETSI)/)
-          type = "ISO"
-          text.match(/[^(]+/).to_s.strip.squeeze(" ")
-        else
-          pubid = Pubid.parse(text)
-          type = pubid.prefix # == "G" ? "ITU" : pubid.prefix
-          pubid.to_s
-        end => id
-        RelatonBib::DocumentIdentifier.new(type: type, id: id, primary: true)
-      end
+    def self.parse_page(hit, imp: false)
+      new(hit, imp: imp).parse_page
+    end
 
-      # Fetch status.
-      # @param doc [Mechanize::Page]
-      # @return [RelatonBib::DocumentStatus, NilClass]
-      def fetch_status(doc)
-        s = doc.at("//table/tr/td/span[contains(@id, 'Label7')]",
-                   "//p[contains(.,'Status :')]")
-        return unless s
+    # Parse page.
+    # @return [Hash]
+    def parse_page # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+      return unless parser.doc
+
+      ItuBibliographicItem.new(
+        id: fetch_id,
+        fetched: Date.today.to_s,
+        type: "standard",
+        docid: docid,
+        edition: parser.fetch_edition,
+        language: ["en"],
+        script: ["Latn"],
+        title: parser.fetch_titles,
+        doctype: DocumentType.new(type: hit.hit[:type]),
+        docstatus: parser.fetch_status,
+        ics: [], # fetch_ics(doc),
+        date: parser.fetch_dates,
+        contributor: fetch_contributors,
+        editorialgroup: parser.fetch_workgroup,
+        abstract: parser.fetch_abstract,
+        copyright: fetch_copyright,
+        link: parser.fetch_link,
+        relation: parser.fetch_relations,
+        place: ["Geneva"],
+      )
+    end
 
-        status = s.text.include?("In force") ? "Published" : "Withdrawal"
-        RelatonBib::DocumentStatus.new(stage: status)
-      end
+    private
 
-      # Fetch workgroup.
-      # @param code [String]
-      # @param doc [Mechanize::Page]
-      # @return [RelatonItu::EditorialGroup, NilClass]
-      def fetch_workgroup(code, doc)
-        wg = doc.at('//table/tr/td/span[contains(@id, "Label8")]/a')
-        # return unless wg
+    def idrec
+      return @idrec if defined? @idrec
 
-        group = wg && itugroup(wg.text)
-        EditorialGroup.new(
-          bureau: code.match(/(?<=-)./).to_s, group: group
-        )
-      end
+      @idrec = CGI.unescape(hit.hit[:url]).split("/").last.slice(/^\d+(?=-)/)&.to_i
+    end
 
-      # @param name [String]
-      # @return [RelatonItu::ItuGroup]
-      def itugroup(name) # rubocop:disable Metrics/MethodLength
-        if name.include? "Study Group"
-          type = "study-group"
-          acronym = "SG"
-        elsif name.include? "Telecommunication Standardization Advisory Group"
-          type = "tsag"
-          acronym = "TSAG"
+    def parser
+      @parser ||= begin
+        if idrec
+          RecommendationParser.new hit, idrec, imp
         else
-          type = "work-group"
-          acronym = "WG"
-        end
-        ItuGroup.new name: name, type: type, acronym: acronym
-      end
-
-      # Fetch relations.
-      # @param doc [Mechanize::Page]
-      # @return [Array<Hash>]
-      def fetch_relations(doc)
-        doc.xpath('//div[contains(@id, "tab_sup")]//table/tr[position()>2]')
-          .map do |r|
-          ref = r.at('./td/span[contains(@id, "title_e")]/nobr/a')
-          fref = RelatonBib::FormattedRef.new(content: ref.text, language: "en",
-                                              script: "Latn")
-          did = RelatonBib::DocumentIdentifier.new(id: ref.text, type: "ITU")
-          bibitem = ItuBibliographicItem.new(formattedref: fref, docid: [did],
-                                             type: "standard")
-          { type: "complementOf", bibitem: bibitem }
-        end
-      end
-
-      # Fetch titles.
-      # @param doc [Mechanize::Page]
-      # @return [RelatonBib::TypedTitleStringCollection]
-      def fetch_titles(doc)
-        t = doc.at("//td[@class='title']|//div/table[1]/tr[4]/td/strong")
-        return [] unless t
-
-        RelatonBib::TypedTitleString.from_string t.text, "en", "Latn"
-      end
-
-      # Fetch dates
-      # @param doc [Mechanize::Page]
-      # @return [Array<Hash>]
-      def fetch_dates(doc) # rubocop:disable Metrics/CyclomaticComplexity,Metrics/PerceivedComplexity
-        dates = []
-        date = doc.at("//table/tr/td/span[contains(@id, 'Label5')]",
-                      "//p[contains(.,'Approved in')]")
-        pdate = date&.text&.match(/\d{4}-\d{2}-\d{2}/).to_s || ob_date(doc)
-        if pdate && !pdate&.empty?
-          dates << { type: "published", on: pdate }
-        elsif pdate = ob_date(doc)
-          dates << { type: "published", on: pdate }
-        end
-        dates
-      end
-
-      # Scrape Operational Bulletin date.
-      # @param doc [Mechanize::Page]
-      # @return [String]
-      def ob_date(doc)
-        pdate = doc.at('//table/tbody/tr/td[contains(text(), "Year:")]')
-        return unless pdate
-
-        roman_to_arabic pdate.text.match(%r{(?<=Year: )(\d{2}.\w+.)?\d{4}}).to_s
-      end
-
-      # Convert roman month number in string date to arabic number
-      # @param date [String]
-      # @return [String]
-      def roman_to_arabic(date)
-        %r{(?<rmonth>[IVX]+)} =~ date
-        if ROMAN_MONTHS.index(rmonth)
-          month = ROMAN_MONTHS.index(rmonth) + 1
-          Date.parse(date.sub(%r{[IVX]+}, month.to_s)).to_s
-        else date
+          RadioRegulationsParser.new hit
         end
       end
+    end
 
-      # Fetch contributors
-      # @param doc [Mechanize::Page]
-      # @return [Array<Hash>]
-      def fetch_contributors(code)
-        return [] unless code
+    def fetch_id
+      docid.find(&:primary).id.gsub(/[.\s()\/-]/, "")
+    end
 
-        abbrev = code.sub(/-\w\s.*/, "")
-        case abbrev
-        when "ITU"
-          name = "International Telecommunication Union"
-          url = "www.itu.int"
-        end
-        [{ entity: { name: name, url: url, abbreviation: abbrev },
-           role: [type: "publisher"] }]
+    # Fetch docid.
+    # @return [Hash]
+    def docid
+      @docid ||= begin
+        docids = hit.hit[:code].to_s.split(" | ").map { |c| createdocid(c) }
+        docids << createdocid(doc["rec_name"]) if docids.empty?
+        docids
       end
+    end
 
-      # Fetch links.
-      # @param doc [Mechanize::Page]
-      # @return [Array<Hash>]
-      def fetch_link(doc)
-        links = [{ type: "src", content: doc.uri.to_s }]
-        obp_elm = doc.at(
-          '//a[@title="Persistent link to download the PDF file"]',
-          "//font[contains(.,'PDF')]/../..",
-        )
-        links << typed_link("obp", obp_elm) if obp_elm
-        wrd_elm = doc.at("//font[contains(.,'Word')]/../..")
-        links << typed_link("word", wrd_elm) if wrd_elm
-        links
-      end
+    # @param text [String]
+    # @return [RelatonBib::DocumentIdentifier]
+    def createdocid(text) # rubocop:disable Metrics/MethodLength
+      # %r{
+      #   ^(?<code>(?:(?:ITU-\w|ISO/IEC)\s)?[^(:]*)
+      #   (?:\s\(V(?<version>\d+)\))?
+      #   (?:\s\((?:(?<_month>\d{2})/)?(?<_year>\d{4})\))?
+      #   (?::[^(]+\((?<buldate>\d{2}\.\w{1,4}\.\d{4})\))?
+      #   (?:\s(?<corr>(?:Amd|Cor)\.\s?\d+))?
+      #   # (\s\(((?<_cormonth>\d{2})\/)?(?<_coryear>\d{4})\))?
+      # }x =~ text.squeeze(" ")
+      # corr&.sub!(/\.\s?/, " ")
+      # id = [code.sub(/[[:space:]]$/, ""), corr].compact.join " "
+      # id += " (V#{version})" if version
+      # id += " - #{buldate}" if buldate
+      # type = id.match(%r{^\w+}).to_s
+      # type = "ITU" if type == "G"
+      if text.match?(/^(?:ISO|ETSI)/)
+        type = "ISO"
+        text.match(/[^(]+/).to_s.strip.squeeze(" ")
+      else
+        pubid = Pubid.parse(text)
+        type = pubid.prefix # == "G" ? "ITU" : pubid.prefix
+        pubid.to_s
+      end => id
+      RelatonBib::DocumentIdentifier.new(type: type, id: id, primary: true)
+    end
 
-      # @param type [String]
-      # @param elm [Nokogiri::XML::Element]
-      def typed_link(type, elm)
-        {
-          type: type,
-          content: URI.join(HitCollection::DOMAIN, elm[:href].strip).to_s,
-        }
-      end
+    # def fetch_data(url)
+    #   resp = hit.hit_collection.agent.get url
+    #   JSON.parse(resp.body)
+    # rescue Mechanize::ResponseCodeError => e
+    #   Util.error "HTTP Service Unavailable: #{e.message}"
+    #   nil
+    # end
+
+    # Scrape Operational Bulletin date.
+    # @param doc [Mechanize::Page]
+    # @return [String]
+    # def ob_date(doc)
+    #   pdate = doc.at('//table/tbody/tr/td[contains(text(), "Year:")]')
+    #   return unless pdate
+
+    #   roman_to_arabic pdate.text.match(%r{(?<=Year: )(\d{2}.\w+.)?\d{4}}).to_s
+    # end
+
+    # Fetch contributors
+    # @return [Array<Hash>]
+    def fetch_contributors
+      return [] unless hit.hit[:code]
+
+      abbrev = hit.hit[:code].sub(/-\w\s.*/, "")
+      case abbrev
+      when "ITU"
+        name = "International Telecommunication Union"
+        url = "www.itu.int"
+      end
+      [{ entity: { name: name, url: url, abbreviation: abbrev }, role: [type: "publisher"] }]
+    end
 
-      # Fetch copyright.
-      # @param code [String]
-      # @param doc [Mechanize::Page]
-      # @return [Array<Hash>]
-      def fetch_copyright(code, doc)
-        abbreviation = code.match(/^[^-]+/).to_s
-        case abbreviation
-        when "ITU"
-          name = "International Telecommunication Union"
-          url = "www.itu.int"
-        end
-        fdate = doc.at("//table/tr/td/span[contains(@id, 'Label5')]")
-        from = fdate&.text || ob_date(doc)
-        [{ owner: [{ name: name, abbreviation: abbreviation, url: url }],
-           from: from }]
+    # Fetch copyright.
+    # @return [Array<Hash>]
+    def fetch_copyright
+      abbreviation = hit.hit[:code].match(/^[^-]+/).to_s
+      case abbreviation
+      when "ITU"
+        name = "International Telecommunication Union"
+        url = "www.itu.int"
       end
+      [{ owner: [{ name: name, abbreviation: abbreviation, url: url }], from: parser.doc_date }]
     end
   end
 end

data/lib/relaton_itu/version.rb

@@ -1,3 +1,3 @@
 module RelatonItu
-  VERSION = "1.20.1".freeze
+  VERSION = "1.20.3".freeze
 end

data/lib/relaton_itu/xml_parser.rb

@@ -14,8 +14,7 @@ module RelatonItu
       # @param ext [Nokogiri::XML::Element]
       # @return [RelatonItu::EditorialGroup]
       def fetch_editorialgroup(ext)
-        eg = ext.at("./editorialgroup")
-        return unless eg
+        return unless ext && (eg = ext.at "editorialgroup")
 
         EditorialGroup.new(
           bureau: eg.at("bureau")&.text,
@@ -51,8 +50,7 @@ module RelatonItu
       # @param ext [Nokogiri::XML::Element]
       # @return [RelatonItu::StructuredIdentifier]
       def fetch_structuredidentifier(ext)
-        sid = ext.at "./structuredidentifier"
-        return unless sid
+        return unless ext && (sid = ext.at "./structuredidentifier")
 
         br = sid.at("bureau").text
         dn = sid.at("docnumber").text

data/lib/relaton_itu.rb

@@ -1,6 +1,7 @@
 require "mechanize"
 require "parslet"
 require "digest/md5"
+require "relaton/core"
 require "relaton/index"
 require "relaton_bib"
 require "relaton_itu/version"

data/relaton_itu.gemspec

@@ -28,5 +28,6 @@ Gem::Specification.new do |spec|
   spec.add_dependency "mechanize", "~> 2.10"
   spec.add_dependency "parslet", "~> 2.0.0"
   spec.add_dependency "relaton-bib", "~> 1.20.0"
+  spec.add_dependency "relaton-core", "~> 0.0.6"
   spec.add_dependency "relaton-index", "~> 0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-itu
 version: !ruby/object:Gem::Version
-  version: 1.20.1
+  version: 1.20.3
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-01-16 00:00:00.000000000 Z
+date: 2026-01-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -52,6 +52,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.20.0
+- !ruby/object:Gem::Dependency
+  name: relaton-core
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.6
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.6
 - !ruby/object:Gem::Dependency
   name: relaton-index
   requirement: !ruby/object:Gem::Requirement
@@ -104,6 +118,8 @@ files:
 - lib/relaton_itu/itu_group.rb
 - lib/relaton_itu/processor.rb
 - lib/relaton_itu/pubid.rb
+- lib/relaton_itu/radio_regulations_parser.rb
+- lib/relaton_itu/recommendation_parser.rb
 - lib/relaton_itu/scrapper.rb
 - lib/relaton_itu/structured_identifier.rb
 - lib/relaton_itu/util.rb
@@ -129,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.27
+rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
 summary: 'RelatonItu: retrieve ITU Standards for bibliographic use using the BibliographicItem