relaton-iec 0.10.0 → 1.3.0

data/grammars/reqt.rng

@@ -0,0 +1,165 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<grammar xmlns="http://relaxng.org/ns/structure/1.0" datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes">
+  <!--
+    Presupposes isodoc.rnc, is included in it
+    include "isodoc.rnc" { }
+  -->
+  <define name="requirement">
+    <element name="requirement">
+      <ref name="RequirementType"/>
+    </element>
+  </define>
+  <define name="recommendation">
+    <element name="recommendation">
+      <ref name="RequirementType"/>
+    </element>
+  </define>
+  <define name="permission">
+    <element name="permission">
+      <ref name="RequirementType"/>
+    </element>
+  </define>
+  <define name="RequirementType">
+    <optional>
+      <attribute name="obligation">
+        <ref name="ObligationType"/>
+      </attribute>
+    </optional>
+    <optional>
+      <attribute name="unnumbered">
+        <data type="boolean"/>
+      </attribute>
+    </optional>
+    <optional>
+      <attribute name="subsequence"/>
+    </optional>
+    <attribute name="id">
+      <data type="ID"/>
+    </attribute>
+    <optional>
+      <attribute name="filename"/>
+    </optional>
+    <optional>
+      <ref name="reqtitle"/>
+    </optional>
+    <optional>
+      <ref name="label"/>
+    </optional>
+    <optional>
+      <ref name="subject"/>
+    </optional>
+    <optional>
+      <ref name="reqinherit"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="classification"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <choice>
+        <ref name="measurementtarget"/>
+        <ref name="specification"/>
+        <ref name="verification"/>
+        <ref name="import"/>
+        <ref name="description"/>
+      </choice>
+    </zeroOrMore>
+    <optional>
+      <ref name="reqt_references"/>
+    </optional>
+    <zeroOrMore>
+      <choice>
+        <ref name="requirement"/>
+        <ref name="recommendation"/>
+        <ref name="permission"/>
+      </choice>
+    </zeroOrMore>
+  </define>
+  <define name="reqtitle">
+    <element name="title">
+      <ref name="FormattedString"/>
+    </element>
+  </define>
+  <define name="label">
+    <element name="label">
+      <text/>
+    </element>
+  </define>
+  <define name="subject">
+    <element name="subject">
+      <text/>
+    </element>
+  </define>
+  <define name="reqinherit">
+    <element name="inherit">
+      <text/>
+    </element>
+  </define>
+  <define name="measurementtarget">
+    <element name="measurement-target">
+      <ref name="RequirementSubpart"/>
+    </element>
+  </define>
+  <define name="specification">
+    <element name="specification">
+      <ref name="RequirementSubpart"/>
+    </element>
+  </define>
+  <define name="verification">
+    <element name="verification">
+      <ref name="RequirementSubpart"/>
+    </element>
+  </define>
+  <define name="import">
+    <element name="import">
+      <ref name="RequirementSubpart"/>
+    </element>
+  </define>
+  <define name="description">
+    <element name="description">
+      <ref name="RequirementSubpart"/>
+    </element>
+  </define>
+  <define name="reqt_references">
+    <element name="references">
+      <oneOrMore>
+        <ref name="bibitem"/>
+      </oneOrMore>
+    </element>
+  </define>
+  <define name="RequirementSubpart">
+    <optional>
+      <attribute name="type"/>
+    </optional>
+    <optional>
+      <attribute name="exclude">
+        <data type="boolean"/>
+      </attribute>
+    </optional>
+    <oneOrMore>
+      <ref name="BasicBlock"/>
+    </oneOrMore>
+  </define>
+  <define name="ObligationType">
+    <choice>
+      <value>requirement</value>
+      <value>recommendation</value>
+      <value>permission</value>
+    </choice>
+  </define>
+  <define name="classification">
+    <element name="classification">
+      <ref name="classification_tag"/>
+      <ref name="classification_value"/>
+    </element>
+  </define>
+  <define name="classification_tag">
+    <element name="tag">
+      <text/>
+    </element>
+  </define>
+  <define name="classification_value">
+    <element name="value">
+      <text/>
+    </element>
+  </define>
+</grammar>

data/lib/relaton_iec.rb

@@ -1,14 +1,21 @@
+require "relaton_iso_bib"
+require "relaton_iec/hit"
+require "nokogiri"
+require "net/http"
 require "relaton_iec/version"
 require "relaton_iec/iec_bibliography"
-
-# if defined? Relaton
-#   require "relaton_iec/processor"
-#   # don't register the gem if it's required form relaton's registry
-#   return if caller.detect { |c| c.include? "register_gems" }
-
-#   Relaton::Registry.instance.register(RelatonIec::Processor)
-# end
+require "relaton_iec/iec_bibliographic_item"
+require "relaton_iec/xml_parser"
+require "relaton_iec/hash_converter"
+require "digest/md5"
 
 module RelatonIec
-  # Your code goes here...
+  # Returns hash of XML reammar
+  # @return [String]
+  def self.grammar_hash
+    gem_path = File.expand_path "..", __dir__
+    grammars_path = File.join gem_path, "grammars", "*"
+    grammars = Dir[grammars_path].sort.map { |gp| File.read gp }.join
+    Digest::MD5.hexdigest grammars
+  end
 end

data/lib/relaton_iec/hash_converter.rb

@@ -0,0 +1,14 @@
+module RelatonIec
+  class HashConverter < RelatonIsoBib::HashConverter
+    class << self
+      #
+      # Ovverides superclass's method
+      #
+      # @param item [Hash]
+      # @retirn [RelatonIec::IecBibliographicItem]
+      def bib_item(item)
+        IecBibliographicItem.new(item)
+      end
+    end
+  end
+end

data/lib/relaton_iec/hit.rb

@@ -4,7 +4,7 @@ module RelatonIec
   # Hit.
   class Hit < RelatonBib::Hit
     # Parse page.
-    # @return [Isobib::IsoBibliographicItem]
+    # @return [RelatonIec::IecBibliographicItem]
     def fetch
       @fetch ||= Scrapper.parse_page @hit
     end

data/lib/relaton_iec/hit_collection.rb

@@ -6,7 +6,6 @@ require "addressable/uri"
 module RelatonIec
   # Page of hit collection.
   class HitCollection < RelatonBib::HitCollection
-
     DOMAIN = "https://webstore.iec.ch"
 
     # @param ref_nbr [String]

data/lib/relaton_iec/iec_bibliographic_item.rb

@@ -0,0 +1,9 @@
+module RelatonIec
+  class IecBibliographicItem < RelatonIsoBib::IsoBibliographicItem
+    TYPES = %w[
+      international-standard technical-specification technical-report
+      publicly-available-specification international-workshop-agreement
+      guide
+    ].freeze
+  end
+end

data/lib/relaton_iec/iec_bibliography.rb

@@ -17,15 +17,10 @@ module RelatonIec
         raise RelatonBib::RequestError, "Could not access http://www.iec.ch"
       end
 
-      # @param text [String]
-      # @return [Array<IsoBibliographicItem>]
-      # def search_and_fetch(text, year = nil)
-      #   Scrapper.get(text, year)
-      # end
-
       # @param code [String] the ISO standard Code to look up (e..g "ISO 9000")
       # @param year [String] the year the standard was published (optional)
-      # @param opts [Hash] options; restricted to :all_parts if all-parts reference is required
+      # @param opts [Hash] options; restricted to :all_parts if all-parts
+      #   reference is required
       # @return [String] Relaton XML serialisation of reference
       def get(code, year = nil, opts = {})
         if year.nil?
@@ -72,7 +67,7 @@ module RelatonIec
         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] }
+        workers.result.sort_by { |a| a[:i] }.map { |x| x[:hit] }
       end
 
       def isobib_search_filter(code)

data/lib/relaton_iec/processor.rb

@@ -12,28 +12,28 @@ module RelatonIec
     # @param code [String]
     # @param date [String, NilClass] year
     # @param opts [Hash]
-    # @return [RelatonIsoBib::IsoBibliographicItem]
+    # @return [RelatonIsoBib::IecBibliographicItem]
     def get(code, date, opts)
       ::RelatonIec::IecBibliography.get(code, date, opts)
     end
 
     # @param xml [String]
-    # @return [RelatonIsoBib::IsoBibliographicItem]
+    # @return [RelatonIsoBib::IecBibliographicItem]
     def from_xml(xml)
-      RelatonIsoBib::XMLParser.from_xml xml
+      RelatonIec::XMLParser.from_xml xml
     end
 
     # @param hash [Hash]
-    # @return [RelatonIsoBib::IsoBibliographicItem]
+    # @return [RelatonIsoBib::IecBibliographicItem]
     def hash_to_bib(hash)
-      item_hash = ::RelatonIsoBib::HashConverter.hash_to_bib(hash)
-      ::RelatonIsoBib::IsoBibliographicItem.new item_hash
+      item_hash = ::RelatonIec::HashConverter.hash_to_bib(hash)
+      ::RelatonIec::IecBibliographicItem.new item_hash
     end
 
     # Returns hash of XML grammar
     # @return [String]
     def grammar_hash
-      @grammar_hash ||= ::RelatonIsoBib.grammar_hash
+      @grammar_hash ||= ::RelatonIec.grammar_hash
     end
   end
 end

data/lib/relaton_iec/scrapper.rb

@@ -1,10 +1,5 @@
 # frozen_string_literal: true
 
-require "relaton_iso_bib"
-require "relaton_iec/hit"
-require "nokogiri"
-require "net/http"
-
 # Capybara.request_driver :poltergeist do |app|
 #   Capybara::Poltergeist::Driver.new app, js_errors: false
 # end
@@ -12,7 +7,6 @@ require "net/http"
 
 module RelatonIec
   # Scrapper.
-  # rubocop:disable Metrics/ModuleLength
   module Scrapper
     DOMAIN = "https://webstore.iec.ch"
 
@@ -32,31 +26,22 @@ module RelatonIec
     }.freeze
 
     class << self
-      # @param text [String]
-      # @return [Array<Hash>]
-      # def get(text)
-      #   iso_workers = WorkersPool.new 4
-      #   iso_workers.worker { |hit| iso_worker(hit, iso_workers) }
-      #   algolia_workers = start_algolia_search(text, iso_workers)
-      #   iso_docs = iso_workers.result
-      #   algolia_workers.end
-      #   algolia_workers.result
-      #   iso_docs
-      # end
+      # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
 
       # Parse page.
       # @param hit [Hash]
       # @return [Hash]
-      # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
       def parse_page(hit_data)
         doc = get_page hit_data[:url]
 
         # Fetch edition.
-        edition = doc.at("//th[contains(., 'Edition')]/following-sibling::td/span").text
+        edition = doc.at(
+          "//th[contains(., 'Edition')]/following-sibling::td/span",
+        ).text
 
         status, relations = fetch_status_relations hit_data[:url]
 
-        RelatonIsoBib::IsoBibliographicItem.new(
+        IecBibliographicItem.new(
           fetched: Date.today.to_s,
           docid: [RelatonBib::DocumentIdentifier.new(id: hit_data[:code], type: "IEC")],
           structuredidentifier: fetch_structuredidentifier(doc),
@@ -81,46 +66,6 @@ module RelatonIec
 
       private
 
-      # Start search workers.
-      # @param text[String]
-      # @param iec_workers [Isobib::WorkersPool]
-      # @reaturn [Isobib::WorkersPool]
-      # def start_algolia_search(text, iec_workers)
-      #   index = Algolia::Index.new 'all_en'
-      #   workers = WorkersPool.new
-      #   workers.worker do |page|
-      #     algolia_worker(index, text, page, workers, iec_workers)
-      #   end
-
-      #   # Add first page so search worker will start.
-      #   workers << 0
-      # end
-
-      # Fetch ISO documents.
-      # @param hit [Hash]
-      # @param isiso_workers [Isobib::WorkersPool]
-      # def iso_worker(hit, iso_workers)
-      #   print "Parse #{iso_workers.size} of #{iso_workers.nb_hits}  \r"
-      #   parse_page hit
-      # end
-
-      # Fetch hits from algolia search service.
-      # @param index[Algolia::Index]
-      # @param text [String]
-      # @param page [Integer]
-      # @param algolia_workers [Isobib::WorkersPool]
-      # @param isiso_workers [Isobib::WorkersPool]
-      # def algolia_worker(index, text, page, algolia_workers, iso_workers)
-      #   res = index.search text, facetFilters: ['category:standard'], page: page
-      #   next_page = res['page'] + 1
-      #   algolia_workers << next_page if next_page < res['nbPages']
-      #   res['hits'].each do |hit|
-      #     iso_workers.nb_hits = res['nbHits']
-      #     iso_workers << hit
-      #   end
-      #   iso_workers.end unless next_page < res['nbPages']
-      # end
-
       # Fetch abstracts.
       # @param doc [Nokigiri::HTML::Document]
       # @return [Array<Array>]
@@ -134,19 +79,6 @@ module RelatonIec
         }]
       end
 
-      # Get langs.
-      # @param doc [Nokogiri::HTML::Document]
-      # @return [Array<Hash>]
-      # def langs(doc)
-      #   lgs = [{ lang: 'en' }]
-      #   doc.css('ul#lang-switcher ul li a').each do |lang_link|
-      #     lang_path = lang_link.attr('href')
-      #     lang = lang_path.match(%r{^\/(fr)\/})
-      #     lgs << { lang: lang[1], path: lang_path } if lang
-      #   end
-      #   lgs
-      # end
-
       # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
 
       # Get page.
@@ -154,25 +86,20 @@ module RelatonIec
       # @return [Array<Nokogiri::HTML::Document, String>]
       def get_page(url)
         uri = URI url
-        resp = Net::HTTP.get_response(uri) # .encode("UTF-8")
+        resp = Net::HTTP.get_response(uri)
         case resp.code
         when "301"
           path = resp["location"]
           url = DOMAIN + path
           uri = URI url
-          resp = Net::HTTP.get_response(uri) # .encode("UTF-8")
+          resp = Net::HTTP.get_response(uri)
         when "404"
           raise RelatonBib::RequestError, "Page not found #{url}"
         end
-        # n = 0
-        # while resp.body !~ /<strong/ && n < 10
-        #   resp = Net::HTTP.get_response(uri)#.encode("UTF-8")
-        #   n += 1
-        # end
         Nokogiri::HTML(resp.body)
-      rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET, EOFError,
-             Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError, Net::ProtocolError,
-             OpenSSL::SSL::SSLError
+      rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET,
+             EOFError, Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError,
+             Net::ProtocolError, OpenSSL::SSL::SSLError
         raise RelatonBib::RequestError, "Could not access #{url}"
       end
       # rubocop:enable Metrics/AbcSize
@@ -211,15 +138,12 @@ module RelatonIec
           statuses = YAML.load_file "lib/relaton_iec/statuses.yml"
           s = wip.at("STAGE").text
           stage, substage = statuses[s]["stage"].split "."
-          # status = statuses[s]["status"]
         else
-          # status   = "Published"
           stage    = "60"
           substage = "60"
         end
         RelatonBib::DocumentStatus.new(stage: stage, substage: substage)
       end
-      # rubocop:enable Metrics/MethodLength
 
       # Fetch workgroup.
       # @param doc [Nokogiri::HTML::Document]
@@ -237,27 +161,26 @@ module RelatonIec
           }],
         }
       end
+      # rubocop:enable Metrics/MethodLength
 
       # Fetch relations.
       # @param doc [Nokogiri::HTML::Document]
       # @return [Array<Hash>]
       # rubocop:disable Metrics/MethodLength
       def fetch_relations(doc)
-        doc.xpath('//ROW[STATUS[.!="PREPARING"]][STATUS[.!="PUBLISHED"]]').map do |r|
+        doc.xpath('//ROW[STATUS[.!="PREPARING"]][STATUS[.!="PUBLISHED"]]').
+          map do |r|
           r_type = r.at("STATUS").text.downcase
           type = case r_type
-                #  when 'published' then 'obsoletes' # Valid
+                 # when 'published' then 'obsoletes' # Valid
                  when "revised", "replaced" then "updates"
                  when "withdrawn" then "obsoletes"
                  else r_type
                  end
-          # url = DOMAIN + "/publication/" + r.at("PUB_ID").text
           fref = RelatonBib::FormattedRef.new(
             content: r.at("FULL_NAME").text, format: "text/plain",
           )
-          bibitem = RelatonIsoBib::IsoBibliographicItem.new(
-            formattedref: fref,
-          )
+          bibitem = IecBibliographicItem.new(formattedref: fref)
           { type: type, bibitem: bibitem }
         end
       end
@@ -272,22 +195,6 @@ module RelatonIec
         status = fetch_status doc
         relations = fetch_relations doc
         [status, relations]
-        # doc.css('ul.steps li').inject([]) do |a, r|
-        #   r_type = r.css('strong').text
-        #   type = case r_type
-        #          when 'Previously', 'Will be replaced by' then 'obsoletes'
-        #          when 'Corrigenda/Amendments', 'Revised by', 'Now confirmed'
-        #            'updates'
-        #          else r_type
-        #          end
-        #   if ['Now', 'Now under review'].include? type
-        #     a
-        #   else
-        #     a + r.css('a').map do |id|
-        #       { type: type, identifier: id.text, url: id['href'] }
-        #     end
-        #   end
-        # end
       end
       # rubocop:enable Metrics/MethodLength
 
@@ -295,66 +202,18 @@ module RelatonIec
       # @param doc [Nokogiri::HTML::Document]
       # @return [String]
       def fetch_type(doc)
-        doc.at('//th[contains(., "Publication type")]/following-sibling::td/span').
-          text.downcase.tr " ", "-"
-        # 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)
-        # #return "international-standard" if type_match.nil?
-        # if TYPES[type_match[2]]
-        #   TYPES[type_match[2]]
-        # elsif type_match[1]
-        # elsif type_match[1] == 'ISO'
-        #   'international-standard'
-        # elsif type_match[1] == 'IWA'
-        #   'international-workshop-agreement'
-        # end
-        # # rescue => _e
-        # #   puts 'Unknown document type: ' + title
+        doc.at(
+          '//th[contains(., "Publication type")]/following-sibling::td/span',
+        ).text.downcase.tr " ", "-"
       end
 
       # Fetch titles.
       # @param hit_data [Hash]
       # @return [Array<Hash>]
       def fetch_titles(hit_data)
-        titles = hit_data[:title].split " - "
-        case titles.size
-        when 0
-          intro, main, part = nil, "", nil
-        when 1
-          intro, main, part = nil, titles[0], nil
-        when 2
-          if /^(Part|Partie) \d+:/ =~ titles[1]
-            intro, main, part = nil, titles[0], titles[1]
-          else
-            intro, main, part = titles[0], titles[1], nil
-          end
-        when 3
-          if /^(Part|Partie) \d+:/ =~ titles[1]
-            intro, main, part = nil, titles[0], titles[1..2].join(" - ")
-          else
-            intro, main, part = titles[0], titles[1], titles[2]
-          end
-        else
-          intro, main, part = titles[0], titles[1], titles[2..-1]&.join(" -- ")
-        end
-        [{
-          title_intro: intro,
-          title_main:  main,
-          title_part:  part,
-          language:    "en",
-          script:      "Latn"
-        }]
+        RelatonBib::TypedTitleString.from_string hit_data[:title], "en", "Latn"
       end
 
-      # Return ISO script code.
-      # @param lang [String]
-      # @return [String]
-      # def script(lang)
-      #   case lang
-      #   when 'en', 'fr' then 'Latn'
-      #   end
-      # end
-
       # Fetch dates
       # @param doc [Nokogiri::HTML::Document]
       # @return [Array<Hash>]
@@ -367,6 +226,8 @@ module RelatonIec
         dates
       end
 
+      # rubocop:disable Metrics/MethodLength
+
       def fetch_contributors(code)
         code.sub(/\s.*/, "").split("/").map do |abbrev|
           case abbrev
@@ -381,12 +242,15 @@ module RelatonIec
             role: [type: "publisher"] }
         end
       end
+      # rubocop:enable Metrics/MethodLength
 
       # Fetch ICS.
       # @param doc [Nokogiri::HTML::Document]
       # @return [Array<Hash>]
       def fetch_ics(doc)
-        doc.xpath('//th[contains(text(), "ICS")]/following-sibling::td/a').map do |i|
+        doc.xpath(
+          '//th[contains(text(), "ICS")]/following-sibling::td/a',
+        ).map do |i|
           code = i.text.match(/[\d\.]+/).to_s.split "."
           { field: code[0], group: code[1], subgroup: code[2] }
         end
@@ -403,9 +267,11 @@ module RelatonIec
         links
       end
 
+      # rubocop:disable Metrics/MethodLength
+
       # Fetch copyright.
       # @param title [String]
-      # @return [Hash]
+      # @return [Array<Hash>]
       def fetch_copyright(code, doc)
         abbreviation = code.match(/.*?(?=\s)/).to_s
         case abbreviation
@@ -415,12 +281,15 @@ module RelatonIec
         end
         from = code.match(/(?<=:)\d{4}/).to_s
         if from.empty?
-          from = doc.xpath("//span[@itemprop='releaseDate']").text
-            .match(/\d{4}/).to_s
+          from = doc.xpath("//span[@itemprop='releaseDate']").text.
+            match(/\d{4}/).to_s
         end
-        { owner: { name: name, abbreviation: abbreviation, url: url }, from: from }
+        [{
+          owner: [{ name: name, abbreviation: abbreviation, url: url }],
+          from: from,
+        }]
       end
+      # rubocop:enable Metrics/MethodLength
     end
   end
-  # rubocop:enable Metrics/ModuleLength
 end