relaton-iso 0.5.2 → 0.5.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 251529f7af2fbfc0a28760e6f7100a3245091229
-  data.tar.gz: d9be71b4df57130f0437b9112072741c37cd9b08
+  metadata.gz: dd542380eec781e5113ea5455b3f0b528188306d
+  data.tar.gz: e457fa95214e668f42a2eda1a1ba5f0cef1e54a1
 SHA512:
-  metadata.gz: e4fc36c5c32d790c39f7b34034960fb73da5329f1ef2f63af2a0417dd8663e915a622a9981abc10cdf334f8dbda5db12708cd3f162428ba8a9283984de3b2793
-  data.tar.gz: eaeadce774f686eaedfcc096071e4fe03b25b72f8c76b702ad302eb21e659ddf5d26d49411064aa5c5c75a3fe1e44dbc86bcc3ec049c116c1ee6fa0b37304acf
+  metadata.gz: d15d13af842f09e14b48ae43c82ae362b37df6394da6b84bc146c359be029ee207bd5dc5ae87691c33d9951d4c4ff86a04542355780fb4a7918848ef665469cd
+  data.tar.gz: 4c0b4c5d1ac62f9418b611a59991c89cf7e29cfa1614319341162aed676d80ad7dc88f13438f1ae83010a09838d971b826e4d517b1a3f5212e863e93b9470b16

data/.travis.yml

@@ -6,6 +6,7 @@ os:
 - linux
 - osx
 rvm:
+- 2.6
 - 2.5
 - 2.4
 - ruby-head

data/Gemfile.lock

@@ -1,8 +1,7 @@
 PATH
   remote: .
   specs:
-    relaton-iso (0.5.2)
-      algoliasearch
+    relaton-iso (0.5.4)
       relaton-iec (~> 0.3.0)
       relaton-iso-bib (~> 0.2.0)
 
@@ -11,14 +10,11 @@ GEM
   specs:
     addressable (2.6.0)
       public_suffix (>= 2.0.2, < 4.0)
-    algoliasearch (1.26.0)
-      httpclient (~> 2.8, >= 2.8.3)
-      json (>= 1.5.1)
     byebug (11.0.1)
     coderay (1.1.2)
     crack (0.4.3)
       safe_yaml (~> 1.0.0)
-    debase (0.2.2)
+    debase (0.2.3)
       debase-ruby_core_source (>= 0.10.2)
     debase-ruby_core_source (0.10.5)
     diff-lcs (1.3)
@@ -26,13 +22,12 @@ GEM
     equivalent-xml (0.6.0)
       nokogiri (>= 1.4.3)
     hashdiff (0.4.0)
-    httpclient (2.8.3)
     isoics (0.1.7)
     json (2.2.0)
     method_source (0.9.2)
-    mini_portile2 (2.3.0)
-    nokogiri (1.8.5)
-      mini_portile2 (~> 2.3.0)
+    mini_portile2 (2.4.0)
+    nokogiri (1.10.3)
+      mini_portile2 (~> 2.4.0)
     pry (0.12.2)
       coderay (~> 1.1.0)
       method_source (~> 0.9.0)
@@ -41,22 +36,21 @@ GEM
       pry (~> 0.10)
     public_suffix (3.1.1)
     rake (10.5.0)
-    relaton-bib (0.2.3)
+    relaton-bib (0.2.5)
       addressable
-      nokogiri (~> 1.8.4)
-    relaton-iec (0.3.1)
+      nokogiri (~> 1.10)
+    relaton-iec (0.3.2)
       addressable
       relaton-iso-bib (~> 0.2.0)
-    relaton-iso-bib (0.2.3)
+    relaton-iso-bib (0.2.4)
       isoics (~> 0.1.6)
-      nokogiri (~> 1.8.4)
       relaton-bib (~> 0.2.0)
       ruby_deep_clone (~> 0.8.0)
     rspec (3.8.0)
       rspec-core (~> 3.8.0)
       rspec-expectations (~> 3.8.0)
       rspec-mocks (~> 3.8.0)
-    rspec-core (3.8.1)
+    rspec-core (3.8.2)
       rspec-support (~> 3.8.0)
     rspec-expectations (3.8.4)
       diff-lcs (>= 1.2.0, < 2.0)
@@ -69,7 +63,7 @@ GEM
       rake (>= 0.8.1)
     ruby_deep_clone (0.8.0)
     safe_yaml (1.0.5)
-    simplecov (0.16.1)
+    simplecov (0.17.0)
       docile (~> 1.1)
       json (>= 1.8, < 3)
       simplecov-html (~> 0.10.0)

data/appveyor.yml

@@ -7,6 +7,7 @@ cache:
 
 environment:
   matrix:
+    - RUBY_VERSION: 26
     - RUBY_VERSION: 25
     - RUBY_VERSION: 24
     - RUBY_VERSION: _trunk

data/lib/relaton_iso/hit.rb

@@ -29,15 +29,12 @@ module RelatonIso
 
     # @return [String]
     def inspect
-      matched_words = @hit["_highlightResult"].
-        reduce([]) { |a, (_k, v)| a + v["matchedWords"] }.uniq
+      # matched_words = @hit["_highlightResult"].
+      #   reduce([]) { |a, (_k, v)| a + v["matchedWords"] }.uniq
 
       "<#{self.class}:#{format('%#.14x', object_id << 1)} "\
-      "@text=\"#{@hit_collection&.hit_pages&.text}\" "\
-      "@fullIdentifier=\"#{@fetch&.shortref}\" "\
-      "@matchedWords=#{matched_words} "\
-      "@category=\"#{@hit['category']}\" "\
-      "@title=\"#{@hit['title']}\">"
+      "@text=\"#{@hit_collection&.ref}\" "\
+      "@reference=\"#{@hit["docRef"]}\""
     end
 
     # @param builder [Nokogiri::XML::Builder]

data/lib/relaton_iso/hit_collection.rb

@@ -6,37 +6,66 @@ module RelatonIso
   # Page of hit collection.
   class HitCollection < Array
     # @return [TrueClass, FalseClass]
-    attr_reader :fetched
+    # attr_reader :fetched
 
     # @return [RelatonIso::HitPages]
-    attr_reader :hit_pages
+    # attr_reader :hit_pages
+
+    # @return [String]
+    attr_reader :ref
 
     # @param hits [Array<Hash>]
-    def initialize(hits, hit_pages = nil)
-      concat(hits.map { |h| Hit.new(h, self) })
-      @fetched = false
-      @hit_pages = hit_pages
+    def initialize(ref)
+      # concat(hits.map { |h| Hit.new(h, self) })
+      # @fetched = false
+      # @hit_pages = hit_pages
+      @ref = ref
+      %r{(?<num>\d+)(-(?<part>\d+))?} =~ ref
+      http = Net::HTTP.new "www.iso.org", 443
+      http.use_ssl = true
+      search = ["status=ENT_ACTIVE,ENT_PROGRESS,ENT_INACTIVE,ENT_DELETED"]
+      search << "docNumber=#{num}"
+      search << "docPartNo=#{part}" if part
+      q = search.join "&"
+      resp = http.get(
+        "/cms/render/live/en/sites/isoorg.advancedSearch.do?#{q}",
+        { 'Accept' => 'application/json, text/plain, */*' }
+      )
+      json = JSON.parse resp.body
+      concat(json["standards"].map { |h| Hit.new h, self })
     end
 
     # @return [RelatonIso::HitCollection]
-    def fetch
-      workers = RelatonBib::WorkersPool.new 4
-      workers.worker(&:fetch)
-      each do |hit|
-        workers << hit
-      end
-      workers.end
-      workers.result
-      @fetched = true
-      self
-    end
+    # def fetch
+    #   workers = RelatonBib::WorkersPool.new 4
+    #   workers.worker(&:fetch)
+    #   each do |hit|
+    #     workers << hit
+    #   end
+    #   workers.end
+    #   workers.result
+    #   @fetched = true
+    #   self
+    # end
 
     def to_s
       inspect
     end
 
     def inspect
-      "<#{self.class}:#{format('%#.14x', object_id << 1)} @fetched=#{@fetched}>"
+      "<#{self.class}:#{format('%#.14x', object_id << 1)} @ref=#{@ref}>"
+    end
+
+    def to_xml(**opts)
+      builder = Nokogiri::XML::Builder.new(encoding: "UTF-8") do |xml|
+        xml.documents do
+          each do |hit|
+            hit.fetch
+            hit.to_xml xml, **opts
+          end
+        end
+      end
+      builder.to_xml
     end
   end
 end

data/lib/relaton_iso/iso_bibliography.rb

@@ -2,7 +2,7 @@
 
 # require 'relaton_iso/iso_bibliographic_item'
 require "relaton_iso/scrapper"
-require "relaton_iso/hit_pages"
+require "relaton_iso/hit_collection"
 require "relaton_iec"
 
 module RelatonIso
@@ -12,10 +12,9 @@ module RelatonIso
       # @param text [String]
       # @return [RelatonIso::HitPages]
       def search(text)
-        HitPages.new text
-      rescue Algolia::AlgoliaProtocolError, SocketError
-        # warn "Could not access http://www.iso.org"
-        # []
+        HitCollection.new text
+      rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET, EOFError,
+             Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError, Net::ProtocolError
         raise RelatonBib::RequestError, "Could not access http://www.iso.org"
       end
 
@@ -34,7 +33,7 @@ module RelatonIso
         %r{
           ^(?<code1>[^\s]+\s[^/]+) # match code
           /?
-          (?<corr>(Amd|CD Amd|Cor|CD Cor)\s\d+:?(\d{4})?(/Cor \d+:\d{4})?) # match correction
+          (?<corr>(Amd|DAmd|CD Amd|Cor|CD Cor)\s\d+:?(\d{4})?(/Cor \d+:\d{4})?) # match correction
         }x =~ code
         code = code1 if code1
 
@@ -46,14 +45,9 @@ module RelatonIso
           end
         end
         code += "-1" if opts[:all_parts]
-        return RelatonIec::IecBibliography.get(code, year, opts) if %r[^ISO/IEC DIR].match code
+        return RelatonIec::IecBibliography.get(code, year, opts) if %r[^ISO/IEC DIR] =~ code
 
         ret = isobib_get1(code, year, corr)
-        if ret.nil? && code =~ %r[^ISO\s]
-          c = code.gsub "ISO", "ISO/IEC"
-          warn "Attempting ISO/IEC retrieval"
-          ret = isobib_get1(c, year, corr)
-        end
         return nil if ret.nil?
 
         ret.to_most_recent_reference unless year || opts[:keep_year]
@@ -80,32 +74,63 @@ module RelatonIso
         nil
       end
 
-      def fetch_pages(s, n)
-        workers = RelatonBib::WorkersPool.new n
-        workers.worker { |w| { i: w[:i], hit: w[:hit].fetch } }
-        s.each_with_index { |hit, i| workers << { i: i, hit: hit } }
-        workers.end
-        workers.result.sort { |x, y| x[:i] <=> y[:i] }.map { |x| x[:hit] }
-      end
+      # def fetch_pages(s, n)
+      #   workers = RelatonBib::WorkersPool.new n
+      #   workers.worker { |w| { i: w[:i], hit: w[:hit].fetch } }
+      #   s.each_with_index { |hit, i| workers << { i: i, hit: hit } }
+      #   workers.end
+      #   workers.result.sort { |x, y| x[:i] <=> y[:i] }.map { |x| x[:hit] }
+      # end
 
+      # Search for hits. If no found then trying missed stages and ISO/IEC.
+      #
+      # @param code [String] reference without correction
+      # @param corr [String] correction
+      # @return [Array<RelatonIso::Hit>]
       def isobib_search_filter(code, corr)
-        # docidrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+}
-        # corrigrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+:[0-9]+/}
         warn "fetching #{code}..."
         result = search(code)
-        result.reduce([]) do |ret, page|
-          ret += page.select do |i|
-            i.hit["title"] &&
-              i.hit["title"] =~ %r{^#{code}} && (
-                corr && %r{^#{code}[d-]*(:\d{4})?/#{corr}} =~ i.hit["title"] ||
-                %r{^#{code}[\d-]*(:\d{4})?/} !~ i.hit["title"] && !corr
-              )
+        res = search_code result, code, corr
+        return res unless res.empty?
+
+        # try stages
+        if %r{^\w+/[^/]+\s\d+} =~ code # code like ISO/IEC 123, ISO/IEC/IEE 123
+          res = try_stages(result, corr) do |st|
+            code.sub(%r{^(?<pref>[^\s]+\s)}) { "#{$~[:pref]}#{st} " }
+          end
+          return res unless res.empty?
+        elsif %r{^\w+\s\d+} =~ code # code like ISO 123
+          res = try_stages(result, corr) do |st|
+            code.sub(%r{^(?<pref>\w+)}) { "#{$~[:pref]}/#{st}" }
           end
-          return ret if ret.size > 9
+          return res unless res.empty?
+        end
 
-          ret
+        if %r{^ISO\s} =~ code # try ISO/IEC if ISO not found
+          warn "Attempting ISO/IEC retrieval"
+          c = code.sub "ISO", "ISO/IEC"
+          res = search_code result, c, corr
+        end
+        res
+      end
+
+      def try_stages(result, corr)
+        %w[NP WD CD DIS FDIS PRF IS].each do |st| # try stages
+          warn "Attempting #{st} stage retrieval"
+          c = yield st
+          res = search_code result, c, corr
+          return res unless res.empty?
+        end
+        []
+      end
+
+      def search_code(result, code, corr)
+        result.select do |i|
+          i.hit["docRef"] =~ %r{^#{code}(?!-)} && (
+              corr && %r{^#{code}[\w-]*(:\d{4})?/#{corr}} =~ i.hit["docRef"] ||
+              %r{^#{code}[\w-]*(:\d{4})?/} !~ i.hit["docRef"] && !corr
+            )
         end
-        # []
       end
 
       # Sort through the results from RelatonIso, fetching them three at a time,
@@ -116,17 +141,13 @@ module RelatonIso
       # If no match, returns any years which caused mismatch, for error reporting
       def isobib_results_filter(result, year)
         missed_years = []
-        result.each_slice(3) do |s| # ISO website only allows 3 connections
-          fetch_pages(s, 3).each_with_index do |r, _i|
-            next if r.nil?
-            return { ret: r } if !year
+        result.each do |s|
+          return { ret: s.fetch } if !year
 
-            r.dates.select { |d| d.type == "published" }.each do |d|
-              return { ret: r } if year.to_i == d.on.year
+          %r{:(?<iyear>\d{4})} =~ s.hit["docRef"]
+          return { ret: s.fetch } if iyear == year
 
-              missed_years << d.on.year
-            end
-          end
+          missed_years << iyear
         end
         { years: missed_years }
       end

data/lib/relaton_iso/scrapper.rb

@@ -1,14 +1,10 @@
 # frozen_string_literal: true
 
-require "algoliasearch"
 require "relaton_iso_bib"
 require "relaton_iso/hit"
 require "nokogiri"
 require "net/http"
 
-Algolia.init application_id: "JCL49WV5AR",
-             api_key: "dd1b9e1ab383f4d4817d29cd5e96d3f0"
-
 module RelatonIso
   # Scrapper.
   # rubocop:disable Metrics/ModuleLength
@@ -50,9 +46,8 @@ module RelatonIso
       # @return [Hash]
       # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
       def parse_page(hit_data)
-        return unless hit_data["path"] =~ /\d+$/
-
-        doc, url = get_page "/standard/#{hit_data['path'].match(/\d+$/)}.html"
+        path = "/contents/data/standard#{hit_data["splitPath"]}/#{hit_data["csnumber"]}.html"
+        doc, url = get_page path
 
         # Fetch edition.
         edition = doc&.xpath("//strong[contains(text(), 'Edition')]/..")&.
@@ -67,14 +62,14 @@ module RelatonIso
           language: langs(doc).map { |l| l[:lang] },
           script: langs(doc).map { |l| script(l[:lang]) }.uniq,
           titles: titles,
-          type: fetch_type(hit_data["title"]),
-          docstatus: fetch_status(doc, hit_data["status"]),
+          type: fetch_type(hit_data["docRef"]),
+          docstatus: fetch_status(doc),
           ics: fetch_ics(doc),
-          dates: fetch_dates(doc, hit_data["title"]),
-          contributors: fetch_contributors(hit_data["title"]),
+          dates: fetch_dates(doc, hit_data["docRef"]),
+          contributors: fetch_contributors(hit_data["docRef"]),
           editorialgroup: fetch_workgroup(doc),
           abstract: abstract,
-          copyright: fetch_copyright(hit_data["title"], doc),
+          copyright: fetch_copyright(hit_data["docRef"], doc),
           link: fetch_link(doc, url),
           relations: fetch_relations(doc),
           structuredidentifier: fetch_structuredidentifier(doc),
@@ -227,7 +222,7 @@ module RelatonIso
       # @param doc [Nokogiri::HTML::Document]
       # @param status [String]
       # @return [Hash]
-      def fetch_status(doc, _status)
+      def fetch_status(doc)
         stage, substage = doc.css("li.dropdown.active span.stage-code > strong").text.split "."
         RelatonBib::DocumentStatus.new(stage: stage, substage: substage)
       end
@@ -283,18 +278,18 @@ module RelatonIso
       # rubocop:enable Metrics/MethodLength
 
       # Fetch type.
-      # @param title [String]
+      # @param ref [String]
       # @return [String]
-      def fetch_type(title)
-        type_match = title.match(%r{^(ISO|IWA|IEC)(?:(/IEC|/IEEE|/PRF|
-          /NP)*\s|/)(TS|TR|PAS|AWI|CD|FDIS|NP|DIS|WD|R|Guide|(?=\d+))}x)
+      def fetch_type(ref)
+        %r{
+          ^(?<prefix>ISO|IWA|IEC)
+          (?:(/IEC|/IEEE|/PRF|/NP|/DGuide)*\s|/)
+          (?<type>TS|TR|PAS|AWI|CD|FDIS|NP|DIS|WD|R|Guide|(?=\d+))
+        }x =~ ref
         # return "international-standard" if type_match.nil?
-        if TYPES[type_match[3]]
-          TYPES[type_match[3]]
-        elsif type_match[1] == "ISO"
-          "international-standard"
-        elsif type_match[1] == "IWA"
-          "international-workshop-agreement"
+        if TYPES[type] then TYPES[type]
+        elsif prefix == "ISO" then "international-standard"
+        elsif prefix == "IWA" then "international-workshop-agreement"
         end
         # rescue => _e
         #   puts 'Unknown document type: ' + title
@@ -305,10 +300,11 @@ module RelatonIso
       # @param lang [String]
       # @return [Hash]
       def fetch_title(doc, lang)
-        titles = doc.at("//h3[@itemprop='description'] | //h2[@itemprop='description']").
-          text.split " -- "
-        case titles.size
-        when 0
+        titles = doc.at(
+          "//h3[@itemprop='description'] | //h2[@itemprop='description']",
+        )&.text&.split " -- "
+        case titles&.size
+        when nil, 0
           intro, main, part = nil, "", nil
         when 1
           intro, main, part = nil, titles[0], nil
@@ -344,10 +340,11 @@ module RelatonIso
       # rubocop:disable Metrics/MethodLength
       # Fetch dates
       # @param doc [Nokogiri::HTML::Document]
+      # @param ref [String]
       # @return [Array<Hash>]
-      def fetch_dates(doc, title)
+      def fetch_dates(doc, ref)
         dates = []
-        %r{^[^\s]+\s[\d-]+:(?<ref_date_str>\d{4})} =~ title
+        %r{^[^\s]+\s[\d-]+:(?<ref_date_str>\d{4})} =~ ref
         pub_date_str = doc.xpath("//span[@itemprop='releaseDate']").text
         if ref_date_str
           ref_date = Date.strptime ref_date_str, "%Y"
@@ -368,8 +365,8 @@ module RelatonIso
         dates
       end
 
-      def fetch_contributors(title)
-        title.sub(/\s.*/, "").split("/").map do |abbrev|
+      def fetch_contributors(ref)
+        ref.sub(/\s.*/, "").split("/").map do |abbrev|
           case abbrev
           when "IEC"
             name = "International Electrotechnical Commission"
@@ -400,22 +397,23 @@ module RelatonIso
       # @param url [String]
       # @return [Array<Hash>]
       def fetch_link(doc, url)
-        obp_elms = doc.xpath("//a[contains(@href, '/obp/ui/')]")
-        obp = obp_elms.attr("href").value if obp_elms.any?
-        rss = DOMAIN + doc.xpath("//a[contains(@href, 'rss')]").attr("href").value
-        [
-          { type: "src", content: url },
-          { type: "obp", content: obp },
-          { type: "rss", content: rss },
-        ]
+        links = [{ type: "src", content: url }]
+        obp = doc.at("//a[contains(@href, '/obp/ui/')]")
+        links << { type: "obp", content: obp[:href] } if obp
+        rss = doc.at("//a[contains(@href, 'rss')]")
+        links << { type: "rss", content: DOMAIN + rss[:href] } if rss
+        pub = doc.at "//p[contains(., 'publicly available')]/a"
+        links << { type: "pub", content: pub[:href] } if pub
+        links
       end
 
       # Fetch copyright.
-      # @param title [String]
+      # @param ref [String]
+      # @param doc [Nokogiri::HTML::Document]
       # @return [Hash]
-      def fetch_copyright(title, doc)
-        owner_name = title.match(/.*?(?=\s)/).to_s
-        from = title.match(/(?<=:)\d{4}/).to_s
+      def fetch_copyright(ref, doc)
+        owner_name = ref.match(/.*?(?=\s)/).to_s
+        from = ref.match(/(?<=:)\d{4}/).to_s
         if from.empty?
           from = doc.xpath("//span[@itemprop='releaseDate']").text.match(/\d{4}/).to_s
         end

data/lib/relaton_iso/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RelatonIso
-  VERSION = "0.5.2"
+  VERSION = "0.5.4"
 end

data/relaton_iso.gemspec

@@ -38,7 +38,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "vcr"
   spec.add_development_dependency "webmock"
 
-  spec.add_dependency "algoliasearch"
   spec.add_dependency "relaton-iec", "~> 0.3.0"
   spec.add_dependency "relaton-iso-bib", "~> 0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-iso
 version: !ruby/object:Gem::Version
-  version: 0.5.2
+  version: 0.5.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-07-09 00:00:00.000000000 Z
+date: 2019-07-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -164,20 +164,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: algoliasearch
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: relaton-iec
   requirement: !ruby/object:Gem::Requirement
@@ -245,7 +231,6 @@ files:
 - lib/relaton_iso.rb
 - lib/relaton_iso/hit.rb
 - lib/relaton_iso/hit_collection.rb
-- lib/relaton_iso/hit_pages.rb
 - lib/relaton_iso/iso_bibliography.rb
 - lib/relaton_iso/scrapper.rb
 - lib/relaton_iso/version.rb

data/lib/relaton_iso/hit_pages.rb

@@ -1,96 +0,0 @@
-# frozen_string_literal: true
-
-require "algoliasearch"
-require "relaton_iso/hit_collection"
-
-module RelatonIso
-  # Pages of hits.
-  class HitPages < Array
-    Algolia.init application_id: "JCL49WV5AR",
-                 api_key: "dd1b9e1ab383f4d4817d29cd5e96d3f0"
-
-    # @return [String]
-    attr_reader :text
-
-    # @param text [String]
-    def initialize(text)
-      @text = text
-      @index = Algolia::Index.new "all_en"
-      resp = @index.search(text, facetFilters: ["category:standard"])
-      @nb_pages = resp["nbPages"]
-      self << HitCollection.new(resp["hits"], self)
-    end
-
-    # @return [RelatonIso::HitCollection]
-    def last
-      collection(@nb_pages - 1)
-    end
-
-    # @param i [Integer]
-    # @return [RelatonIso::HitCollection]
-    def [](idx)
-      # collection i
-      return if idx + 1 > @nb_pages
-
-      collection idx
-      super
-    end
-
-    # @return [Array]
-    def map(&block)
-      m = []
-      @nb_pages.times do |n|
-        m << yield(self[n]) if block
-      end
-      m
-    end
-
-    def each(&block)
-      @nb_pages.times do |n|
-        yield self[n] if block
-      end
-    end
-
-    def to_s
-      inspect
-    end
-
-    def inspect
-      "<#{self.class}:#{format('%#.14x', object_id << 1)} @text=#{@text} "\
-      "@pages=#{@nb_pages}>"
-    end
-
-    # @return [Integer]
-    def size
-      @nb_pages
-    end
-
-    def to_xml(**opts)
-      builder = Nokogiri::XML::Builder.new(encoding: "UTF-8") do |xml|
-        xml.documents do
-          each do |page|
-            page.fetch
-            page.each { |hit| hit.to_xml xml, **opts }
-          end
-        end
-      end
-      builder.to_xml
-    end
-
-    private
-
-    # @param i [Integer]
-    # @return [RelatonIso::HitCollection]
-    def collection(idx)
-      return if idx + 1 > @nb_pages
-
-      while Array.instance_method(:size).bind(self).call < idx + 1
-        resp = @index.search(@text,
-                             facetFilters: ["category:standard"],
-                             page: idx)
-        self << HitCollection.new(resp["hits"], self)
-      end
-      Array.instance_method(:[]).bind(self).call idx
-    end
-  end
-end