relaton-itu 2.1.2 → 2.2.0.pre.alpha.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6934a71bcfd52917864d6cf3af90fd07333ce87cc9c5d8cd045217d86a423b28
-  data.tar.gz: 0a1daa40935cb00409c1d40186aa63d7c25bd70866356a635fa52dc4ef512d87
+  metadata.gz: 1c4821cc8b6a9ce8a01c25c40b1f45d719d86fd0d0c0573fe4043a12b17ff9cb
+  data.tar.gz: 5eecc3cf067f12aacda1765adb5dcaf442617c2d30acd79b18739b98697a37b2
 SHA512:
-  metadata.gz: 11d05f246d70e236f0995ec2a80abfef38c8085b602aa6bff5aa4c5033fdc5d4984cec8e9125348f9f31739903cf82e89d9d16819a4233e4855ece1488455366
-  data.tar.gz: 42cfd40edebcd128a3cc402a3c6e3c6fd4b2d7e1bad5a4a9d2403dd59b020cf729034eeaa864d915e69e1bf192b0bb7d2e90ce31465fa7db942dbaa608d3eb7f
+  metadata.gz: b49648210b4649382889aa44a46dfb3b2ee28833bd35f82946e052e0dc7731404a5e03a8f6076735f55676b4dd6a248a6c73014dcae7655bf8e2d14ae62be7c0
+  data.tar.gz: 3dfc18dd9e59e79295f532c27a37c540b0f3a4c8515c6373b8b9823edf568fc5fb39707c24361aa399e9f940afd3701aaa59dacf027a607c527d4a4996510550

data/CLAUDE.md

@@ -45,28 +45,6 @@ All model classes use `Lutaml::Model::Serializable` for XML/YAML serialization:
 - **`DataParserR`** — module that parses ITU-R JSON search API results into `ItemData` instances (sets `flavor: "itu"` on all parsed documents)
 - Sources: recommendations (JSON index), questions, reports, handbooks, resolutions (HTML indices)
 
-### Runtime lookup (`HitCollection#search`)
-
-`Bibliography.get`/`search` routes by reference in `HitCollection#search`:
-
-- **ITU-T Recommendations** (`request_recommendation`) — discovery is a two-stage HTTP flow against
-  `www.itu.int`. The `RunSearch` Deep Search endpoint was removed/WAF-blocked (issue #88), so
-  discovery now GETs the public `ITU-T/recommendations/rec.aspx?rec={code}` page, extracts the
-  record handle (`11.1002/1000/{idrec}`), and calls the `mws/api/recommendations/getRecEditions`
-  API to build one `Hit` per edition (each `hit[:url]` is a `handle.itu.int/.../{idrec}-en` URL so
-  `Scraper#idrec` re-parses it). Year/edition filtering stays in `Bibliography#search_filter` /
-  `#isobib_results_filter`. Full metadata is fetched by `RecommendationParser` (the `mws/api/*`
-  endpoints), unchanged.
-- **ITU-R RR & Operational Bulletins** (`request_publication`) — resolved to their predictable
-  `/pub/{pubid}` landing page (`R-REG-RR-{year}`, `T-SP-OB.{num}-{year}`) and scraped by
-  `RadioRegulationsParser`. A redirect to `notfound.aspx` (or a 404) yields no hit.
-- **ITU-R (other)** (`request_document`) — reads the pre-built `relaton-data-itu-r` GitHub dataset
-  via `Relaton::Index`; does not hit `www.itu.int`.
-
-Note: `DataFetcher` (the offline ITU-R harvester) still POSTs to the removed `RunSearch` endpoint,
-so a dataset *refresh* is currently broken — a follow-up should migrate it (and, longer term, ITU-T)
-to a relaton-data dataset.
-
 ### Processor
 
 `Relaton::Itu::Processor` extends `Relaton::Core::Processor` and is the entry point for the Relaton plugin system. Provides `get`, `fetch_data`, `from_xml`, `hash_to_bib`, `grammar_hash`, and `remove_index_file`.

data/Gemfile

@@ -5,6 +5,14 @@ source "https://rubygems.org"
 # Specify your gem's dependencies in relaton_itu.gemspec
 gemspec
 
+# Use local monorepo sibling gems where available.
+Dir["../*/"].each do |dir|
+  name = File.basename(dir)
+  next if name == File.basename(__dir__)
+  next unless File.exist?(File.join(dir, "#{name}.gemspec"))
+  gem name, path: dir
+end
+
 
 gem "equivalent-xml", "~> 0.6"
 gem "pry-byebug"

data/lib/relaton/itu/hit_collection.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require "cgi"
-require "json"
 require_relative "hit"
 
 module Relaton
@@ -10,16 +8,11 @@ module Relaton
     class HitCollection < Relaton::Core::HitCollection
       DOMAIN = "https://www.itu.int"
       GH_ITU_R = "https://raw.githubusercontent.com/relaton/relaton-data-itu-r/refs/heads/v2/"
-      REC_URL = "#{DOMAIN}/ITU-T/recommendations/rec.aspx?rec=%<rec>s&lang=en".freeze
-      RECEDITIONS_URL = "#{DOMAIN}/mws/api/recommendations/getRecEditions?idrec=%<idrec>s&lang=en".freeze
-      HANDLE_URL = "http://handle.itu.int/11.1002/1000/%<idrec>s-en".freeze
 
       def search
         case ref.to_ref
-        when %r{^ITU-R\sRR}, %r{\bOB\.|Operational Bulletin}
-          request_publication
-        when /^ITU-T/
-          request_recommendation
+        when /^(ITU-T|ITU-R\sRR)/
+          request_search
         when /^ITU-R\s/
           request_document
         end
@@ -34,87 +27,12 @@ module Relaton
 
       private
 
-      # Resolve an ITU-T Recommendation to its editions via the public rec.aspx
-      # page (which exposes the record's handle/idrec) and the getRecEditions API.
-      # One hit is built per edition, mirroring the multi-result shape the old
-      # RunSearch endpoint used to return, so year filtering keeps working.
-      def request_recommendation
+      def request_search
         Util.info "Fetching from www.itu.int ...", key: ref.to_s
-        idrec = fetch_idrec
-        return @array = [] unless idrec
-
-        @array = editions(idrec).map { |ed| recommendation_hit(ed) }
-      end
-
-      # @return [String, nil] the record's idrec, or nil when the code is unknown
-      def fetch_idrec
-        url = format(REC_URL, rec: CGI.escape(rec_query))
-        agent.get(url).body[%r{11\.1002/1000/(\d+)}, 1]
-      rescue Mechanize::ResponseCodeError => e
-        raise unless e.response_code == "404" # unknown code => treat as not found
-
-        nil
-      end
-
-      # @return [String] the `rec=` value for the rec.aspx lookup
-      def rec_query
-        ref.suppl ? "#{ref.code} Suppl. #{ref.suppl}" : ref.code
-      end
-
-      # @param idrec [String]
-      # @return [Array<Hash>] editions of the recommendation
-      def editions(idrec)
-        JSON.parse agent.get(format(RECEDITIONS_URL, idrec: idrec)).body
-      rescue JSON::ParserError
-        []
-      end
-
-      # @param edition [Hash] a getRecEditions entry
-      # @return [Relaton::Itu::Hit]
-      def recommendation_hit(edition)
-        Hit.new({
-          code: "ITU-T #{edition['rec_name']}",
-          title: edition["title"],
-          url: format(HANDLE_URL, idrec: edition["idrec"]),
-          type: "recommendation",
-        }, self)
-      end
-
-      # Resolve an ITU-R Radio Regulation or Operational Bulletin to its stable
-      # /pub landing page, whose id is derivable from the reference.
-      def request_publication
-        Util.info "Fetching from www.itu.int ...", key: ref.to_s
-        return @array = [] unless ref.year
-
-        url = "#{DOMAIN}/pub/#{publication_id}"
-        page = fetch_publication_page url
-        return @array = [] if page.nil? || page.uri.to_s.match?(/notfound/i)
-
-        hit = Hit.new({ code: publication_code, title: nil, url: url, type: "publication" }, self)
-        @array = [hit]
-      end
-
-      # @return [Mechanize::Page, nil] nil when the publication does not exist
-      def fetch_publication_page(url)
-        agent.get url
-      rescue Mechanize::ResponseCodeError => e
-        raise unless e.response_code == "404" # unknown publication => not found
-
-        nil
-      end
-
-      # @return [String] the /pub identifier for RR or OB
-      def publication_id
-        if ref.code == "RR"
-          "R-REG-RR-#{ref.year}"
-        else # Operational Bulletin, e.g. OB.1096
-          "T-SP-OB.#{ref.code[/\d+/]}-#{ref.year}"
-        end
-      end
-
-      # @return [String] the docidentifier-friendly code (year only, no month)
-      def publication_code
-        "#{ref.prefix}-#{ref.sector} #{ref.code} (#{ref.year})"
+        url = "#{DOMAIN}/net4/ITU-T/search/GlobalSearch/RunSearch"
+        data = { json: params.to_json }
+        resp = agent.post url, data
+        @array = hits JSON.parse(resp.body)
       end
 
       def request_document # rubocop:todo Metrics/MethodLength, Metrics/AbcSize
@@ -132,6 +50,78 @@ module Relaton
         hit.item = item
         @array = [hit]
       end
+
+      # @return [String]
+      def group
+        @group ||= case ref.to_ref
+                   when %r{OB|Operational Bulletin}, %r{^ITU-R\sRR}
+                     "Publications"
+                   when %r{^ITU-T} then "Recommendations"
+                   end
+      end
+
+      # @return [Hash]
+      def params # rubocop:disable Metrics/MethodLength
+        input = ref.dup
+        input.year = nil
+        {
+          "Input" => input.to_s,
+          "Start" => 0,
+          "Rows" => 20,
+          "SortBy" => "RELEVANCE",
+          "ExactPhrase" => false,
+          "CollectionName" => "General",
+          "CollectionGroup" => group,
+          "Sector" => ref.to_ref.match(/(?<=^ITU-)\w/).to_s.downcase,
+          "Criterias" => [{
+            "Name" => "Search in",
+            "Criterias" => [
+              {
+                "Selected" => false,
+                "Value" => "",
+                "Label" => "Name",
+                "Target" => "/name_s",
+                "TypeName" => "CHECKBOX",
+                "GetCriteriaType" => 0,
+              },
+              {
+                "Selected" => false,
+                "Value" => "",
+                "Label" => "Short description",
+                "Target" => "/short_description_s",
+                "TypeName" => "CHECKBOX",
+                "GetCriteriaType" => 0,
+              },
+              {
+                "Selected" => false,
+                "Value" => "",
+                "Label" => "File content",
+                "Target" => "/file",
+                "TypeName" => "CHECKBOX",
+                "GetCriteriaType" => 0,
+              },
+            ],
+            "ShowCheckbox" => true,
+            "Selected" => false,
+          }],
+          "Topics" => "",
+          "ClientData" => {},
+          "Language" => "en",
+          "SearchType" => "All",
+        }
+      end
+
+      # @param data [Hash]
+      # @return [Array<Relaton::Itu::Hit>]
+      def hits(data)
+        data["results"].map do |h|
+          code  = h["Media"]["Name"]
+          title = h["Title"]
+          url   = "#{DOMAIN}#{h['Redirection']}"
+          type  = h["Collection"]["Group"].downcase[0...-1]
+          Hit.new({ code: code, title: title, url: url, type: type }, self)
+        end
+      end
     end
   end
 end

data/lib/relaton/itu/radio_regulations_parser.rb

@@ -19,8 +19,7 @@ module Relaton
       end
 
       def doc_url
-        url = CGI.unescape(hit.hit[:url])
-        url.include?("dest=") ? url.split("dest=").last : url
+        CGI.unescape(hit.hit[:url]).split("dest=").last
       end
 
       def fetch_edition = nil

data/lib/relaton/itu/scraper.rb

@@ -91,24 +91,10 @@ module Relaton
         @docid ||= begin
           docids = hit.hit[:code].to_s.split(" | ").map { |c| createdocid(c) }
           docids << createdocid(doc["rec_name"]) if docids.empty?
-          iso = iso_docid
-          docids << iso if iso
           docids
         end
       end
 
-      # The equivalent ISO/IEC identifier used to come from the search result's
-      # media name; it is now re-sourced from the recommendation header's
-      # `iso_number` field (e.g. "Equivalent standard: ISO/IEC 17788:2014 (Common)").
-      # @return [Relaton::Bib::Docidentifier, nil]
-      def iso_docid
-        return unless idrec # only recommendations carry an idrec / iso_number
-
-        num = parser.doc && parser.doc["iso_number"]
-        id = num && num[%r{ISO(?:/IEC)?(?:/IEEE)?\s+\d[\d-]*}]
-        createdocid(id) if id
-      end
-
       # @param text [String]
       # @return [Relaton::Bib::Docidentifier]
       def createdocid(text) # rubocop:disable Metrics/MethodLength

data/lib/relaton/itu/version.rb

@@ -1,5 +1,5 @@
 module Relaton
   module Itu
-    VERSION = "2.1.2".freeze
+    VERSION = "2.2.0.pre.alpha.1".freeze
   end
 end

data/relaton-itu.gemspec

@@ -23,11 +23,11 @@ Gem::Specification.new do |spec|
   spec.bindir        = "exe"
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
-  spec.required_ruby_version = Gem::Requirement.new(">= 3.2.0")
+  spec.required_ruby_version = Gem::Requirement.new(">= 3.3.0")
 
   spec.add_dependency "mechanize", "~> 2.10"
   spec.add_dependency "parslet", "~> 2.0.0"
-  spec.add_dependency "relaton-bib", "~> 2.1.0"
-  spec.add_dependency "relaton-core", "~> 0.0.13"
-  spec.add_dependency "relaton-index", "~> 0.2.0"
+  spec.add_dependency "relaton-bib", "~> 2.2.0.pre.alpha.1"
+  spec.add_dependency "relaton-core", "~> 2.2.0.pre.alpha.1"
+  spec.add_dependency "relaton-index", "~> 2.2.0.pre.alpha.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-itu
 version: !ruby/object:Gem::Version
-  version: 2.1.2
+  version: 2.2.0.pre.alpha.1
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-07-29 00:00:00.000000000 Z
+date: 2026-06-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mechanize
@@ -44,42 +44,42 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.0
+        version: 2.2.0.pre.alpha.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.0
+        version: 2.2.0.pre.alpha.1
 - !ruby/object:Gem::Dependency
   name: relaton-core
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.13
+        version: 2.2.0.pre.alpha.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.0.13
+        version: 2.2.0.pre.alpha.1
 - !ruby/object:Gem::Dependency
   name: relaton-index
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 2.2.0.pre.alpha.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.2.0
+        version: 2.2.0.pre.alpha.1
 description: 'Relaton::Itu: retrieve ITU Standards for bibliographic use using the
   BibliographicItem model'
 email:
@@ -92,7 +92,6 @@ files:
 - ".github/workflows/release.yml"
 - ".gitignore"
 - ".rspec"
-- ".rubocop.yml"
 - CLAUDE.md
 - Gemfile
 - LICENSE.txt
@@ -141,7 +140,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.2.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="

data/.rubocop.yml

@@ -1,12 +0,0 @@
-# This project follows the Ribose OSS style guide.
-# https://github.com/riboseinc/oss-guides
-# All project-specific additions and overrides should be specified in this file.
-
-require: rubocop-rails
-
-inherit_from:
-  - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
-AllCops:
-  TargetRubyVersion: 3.2
-Rails:
-  Enabled: false