relaton-gb 0.12.0 → 1.2.0

data/lib/relaton_gb.rb

@@ -19,4 +19,4 @@ module RelatonGb
     grammars = Dir[grammars_path].sort.map { |gp| File.read gp }.join
     Digest::MD5.hexdigest grammars
   end
-end
+end

data/lib/relaton_gb/gb_bibliographic_item.rb

@@ -35,6 +35,7 @@ module RelatonGb
       @ccs = args[:ccs].map { |c| c.is_a?(Cnccs::Ccs) ? c : Cnccs.fetch(c) }
       @gbtype = GbStandardType.new args[:gbtype]
       @gbplannumber = args[:gbplannumber] || structuredidentifier&.project_number
+      # @doctype = args[:doctype]
     end
 
     # @param builder [Nokogiri::XML::Builder]
@@ -61,9 +62,7 @@ module RelatonGb
 
     # @return [String]
     def inspect
-      "<#{self.class}:#{format('%#.14x', object_id << 1)}>"
-      # "@fullIdentifier=\"#{@fetch&.shortref}\" "\
-      # "@title=\"#{title}\">"
+      "<#{self.class}:#{format('%<id>#.14x', id: object_id << 1)}>"
     end
 
     # @return [String]
@@ -76,34 +75,11 @@ module RelatonGb
 
       id ||= @docidentifier.reject { |i| i.type == "DOI" }[0]
       idstr = id.id
-      # if id.part_number&.size&.positive?
-      #   idstr = idstr + "-#{id.part_number}"
-      # end
       idstr.gsub(/\s/, "").strip
     end
 
     private
 
-    # Overraides IsoBibliographicItem method.
-    # @param language [Array<String>]
-    # @raise ArgumentError
-    def check_language(language)
-      language.each do |lang|
-        unless %w[en zh].include? lang
-          raise ArgumentError, "invalid language: #{lang}"
-        end
-      end
-    end
-
-    # Overraides IsoBibliographicItem method.
-    # @param script [Array<String>]
-    # @raise ArgumentError
-    def check_script(script)
-      script.each do |scr|
-        raise ArgumentError, "invalid script: #{scr}" unless %w[Latn Hans].include? scr
-      end
-    end
-
     # @param builder [Nokogiri::XML::Builder]
     def render_gbxml(builder)
       gbtype.to_xml builder

data/lib/relaton_gb/gb_scrapper.rb

@@ -16,7 +16,7 @@ module RelatonGb
       # @return [RelatonGb::HitCollection]
       def scrape_page(text)
         search_html = OpenURI.open_uri(
-          "http://openstd.samr.gov.cn/bzgk/gb/std_list?p.p2=" + text
+          "http://openstd.samr.gov.cn/bzgk/gb/std_list?p.p2=" + text,
         )
         result = Nokogiri::HTML search_html
         hits = result.xpath(

data/lib/relaton_gb/hash_converter.rb

@@ -17,6 +17,15 @@ module RelatonGb
 
       private
 
+      #
+      # Ovverides superclass's method
+      #
+      # @param item [Hash]
+      # @retirn [RelatonGb::GbBibliographicItem]
+      def bib_item(item)
+        GbBibliographicItem.new(item)
+      end
+
       def ccs_hash_to_bib(ret)
         ret[:ccs] = array(ret[:ccs]).map do |ccs|
           ccs[:code] ? Cnccs.fetch(ccs[:code]) : Cnccs.fetch(ccs)

data/lib/relaton_gb/hit.rb

@@ -38,7 +38,7 @@ module RelatonGb
 
     # @return [String]
     def inspect
-      "<#{self.class}:#{format('%#.14x', object_id << 1)} "\
+      "<#{self.class}:#{format('%<id>#.14x', id: object_id << 1)} "\
       "@fullIdentifier=\"#{@fetch&.shortref}\" "\
       "@docref=\"#{docref}\">"
     end

data/lib/relaton_gb/hit_collection.rb

@@ -5,10 +5,11 @@ module RelatonGb
   class HitCollection < RelatonBib::HitCollection
     # @param hits [Array<Hash>]
     # @param hit_pages [Integer]
-    # @param scrapper [RelatonGb::GbScrapper, RelatonGb::SecScrapper, RelatonGb::TScrapper]
+    # @param scrapper [RelatonGb::GbScrapper, RelatonGb::SecScrapper,
+    #   RelatonGb::TScrapper]
     def initialize(hits = [])
       @array = hits
-      @fetched   = false
+      @fetched = false
     end
   end
 end

data/lib/relaton_gb/scrapper.rb

@@ -55,32 +55,37 @@ module RelatonGb
     # @param docref [Strings]
     # @return [Array<Hash>]
     def get_contributors(doc, docref)
-      gb_en = GbAgencies::Agencies.new("en", {}, "")
-      gb_zh = GbAgencies::Agencies.new("zh", {}, "")
       name = docref.match(/^[^\s]+/).to_s
       name.sub!(%r{/[TZ]$}, "") unless name =~ /^GB/
       gbtype = get_gbtype(doc, docref)
-      entity = RelatonBib::Organization.new name: [
-        { language: "en", content: gb_en.standard_agency1(gbtype[:scope], name, gbtype[:mandate]) },
-        { language: "zh", content: gb_zh.standard_agency1(gbtype[:scope], name, gbtype[:mandate]) },
-      ]
+      orgs = %w[en zh].map { |l| org(l, name, gbtype) }.compact
+      return [] unless orgs.any?
+
+      entity = RelatonBib::Organization.new name: orgs
       [{ entity: entity, role: [type: "publisher"] }]
     end
 
+    # @param lang [String]
+    # @param name [String]
+    # @param gbtype [Hash]
+    # @return [Hash]
+    def org(lang, name, gbtype)
+      ag = GbAgencies::Agencies.new(lang, {}, "")
+      content = ag.standard_agency1(gbtype[:scope], name, gbtype[:mandate])
+      return unless content
+
+      { language: lang, content: content }
+    end
+
     # @param doc [Nokogiri::HTML::Document]
-    # @return [Array<Hash>]
-    #   * :title_intro [String]
-    #   * :title_main [String]
-    #   * :language [String]
-    #   * :script [String]
+    # @return [Array<RelatonBib::TypedTitleString>]
     def get_titles(doc)
-      titles = [{ title_main: doc.at("//td[contains(text(), '中文标准名称')]/b").text,
-                  title_intro: nil, language: "zh", script: "Hans" }]
-      title_main = doc.at("//td[contains(text(), '英文标准名称')]").text.match(/[\w\s]+/).to_s
-      unless title_main.empty?
-        titles << { title_main: title_main, title_intro: nil, language: "en", script: "Latn" }
-      end
-      titles
+      tzh = doc.at("//td[contains(text(), '中文标准名称')]/b").text
+      titles = RelatonBib::TypedTitleString.from_string tzh, "zh", "Hans"
+      ten = doc.at("//td[contains(text(), '英文标准名称')]").text.match(/[\w\s]+/).to_s
+      return titles if ten.empty?
+
+      titles + RelatonBib::TypedTitleString.from_string(ten, "en", "Latn")
     end
 
     def get_type
@@ -113,12 +118,6 @@ module RelatonGb
         mandate: get_mandate(ref), topic: "other" }
     end
 
-    # @param doc [Nokogiri::HTML::Document]
-    # @return [String]
-    # def get_ref(doc)
-    #   doc.xpath('//dt[text()="标准号"]/following-sibling::dd[1]').text
-    # end
-
     # @param doc [Nokogiri::HTML::Document]
     # @return [Array<String>]
     def get_ccs(doc)

data/lib/relaton_gb/sec_scrapper.rb

@@ -58,13 +58,15 @@ module RelatonGb
       #   * :language [String]
       #   * :script [String]
       def get_titles(doc)
-        titles = [{ title_main: doc.at("//h4").text.delete("\r\n\t"),
-                    title_intro: nil, language: "zh", script: "Hans" }]
+        # titles = [{ title_main: doc.at("//h4").text.delete("\r\n\t"),
+        #             title_intro: nil, language: "zh", script: "Hans" }]
+        tzh = doc.at("//h4").text.delete("\r\n\t")
+        RelatonBib::TypedTitleString.from_string tzh, "zh", "Hans"
         # title_main = doc.at("//td[contains(text(), '英文标准名称')]").text.match(/[\w\s]+/).to_s
         # unless title_main.empty?
         #   titles << { title_main: title_main, title_intro: nil, language: "en", script: "Latn" }
         # end
-        titles
+        # titles
       end
 
       # @param _doc [Nokogiri::HTML::Document]

data/lib/relaton_gb/t_scrapper.rb

@@ -84,16 +84,13 @@ module RelatonGb
       end
 
       def get_titles(doc)
-        xpath  = '//td[contains(.,"中文标题")]/following-sibling::td[1]'
-        titles = [{ title_main: doc.xpath(xpath).text,
-                    title_intro: nil, language: "zh", script: "Hans" }]
-        xpath = '//td[contains(.,"英文标题")]/following-sibling::td[1]'
-        title_main = doc.xpath(xpath).text
-        unless title_main.empty?
-          titles << { title_main: title_main, title_intro: nil, language: "en",
-                      script: "Latn" }
-        end
-        titles
+        xpz = '//td[contains(.,"中文标题")]/following-sibling::td[1]'
+        titles = RelatonBib::TypedTitleString.from_string doc.at(xpz).text, "zh", "Hans"
+        xpe = '//td[contains(.,"英文标题")]/following-sibling::td[1]'
+        ten = doc.xpath(xpe).text
+        return titles if ten.empty?
+
+        titles + RelatonBib::TypedTitleString.from_string(ten, "en", "Latn")
       end
 
       def gbtype

data/lib/relaton_gb/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RelatonGb
-  VERSION = "0.12.0"
+  VERSION = "1.2.0"
 end

data/lib/relaton_gb/xml_parser.rb

@@ -3,18 +3,15 @@ require "nokogiri"
 module RelatonGb
   class XMLParser < RelatonIsoBib::XMLParser
     class << self
-      def from_xml(xml)
-        doc = Nokogiri::XML(xml)
-        gbitem = doc.at "/bibitem|/bibdata"
-        if gbitem
-          GbBibliographicItem.new item_data(gbitem)
-        else
-          warn "[relato-gb] can't find bibitem or bibdata element in the XML"
-        end
-      end
-
       private
 
+      # override RelatonBib::BibliographicItem.bib_item method
+      # @param item_hash [Hash]
+      # @return [RelatonGb::GbBibliographicItem]
+      def bib_item(item_hash)
+        GbBibliographicItem.new item_hash
+      end
+
       def item_data(gbitem)
         data = super
         data[:committee] = fetch_committee gbitem
@@ -24,11 +21,6 @@ module RelatonGb
         data
       end
 
-      # Overrade get_id from RelatonIsoBib::XMLParser
-      # def get_id(did)
-      #   did.text.match(/^(?<project>.*?\d+)(?<hyphen>-)?(?(<hyphen>)(?<year>\d*))/)
-      # end
-
       def fetch_committee(doc)
         committee = doc.at "./ext/gbcommittee"
         return nil unless committee

data/relaton_gb.gemspec

@@ -37,5 +37,5 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "cnccs", "~> 0.1.1"
   spec.add_dependency "gb-agencies", "~> 0.0.1"
-  spec.add_dependency "relaton-iso-bib", "~> 0.9.0"
+  spec.add_dependency "relaton-iso-bib", ">= 1.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-gb
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-03-30 00:00:00.000000000 Z
+date: 2020-06-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: debase
@@ -182,16 +182,16 @@ dependencies:
   name: relaton-iso-bib
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.0
+        version: 1.2.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.9.0
+        version: 1.2.0
 description: 'RelatonGb: retrieve Chinese GB Standards for bibliographic use using
   the BibliographicItem model.'
 email: