gbbib 0.1.3 → 0.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: 2967105032707b9f8b1232f232874383d178cac8e37e81564c3f4703706bb042
-  data.tar.gz: 4fe03b886a4af769c90de2100d05d4dbf539b47577f5992b9ad6559f9c2632cb
+SHA1:
+  metadata.gz: eb3b926e47fdfca5623a37e092d8072be696a8fe
+  data.tar.gz: 781ce62f34f01ea01ce1b1bea083ec851beb56e8
 SHA512:
-  metadata.gz: 987c2fdf13dfebb7153d14faa2db1a3aabab8905f2d60978b5d23587a774613884e3509b8047590993c43342b8c7a88c98189b4974c4edc3f3ba06b3da84dec3
-  data.tar.gz: 25be12092031186450f44218b40dfb50d660b7aeadd24da1130b4f190b38c504572156a6550b0f20ce5eb443e6eab428221227ffe7cd61d61398ed2097faa0fd
+  metadata.gz: c19520eb951344e11564dfba80bc16111ef331dc5b46e8bb37a31b1d3892ad56165ed90495eb82a1158e1034f6e05800dc7d40feced12c74f2e067a50e7ce173
+  data.tar.gz: 4b75cfa4a98a855a83800d7c84c207997f008a5d5ab80a655fa5d2098be19ae248dd255afce983b069a7d27d997aa1ac411cd26d26f5c7c31a327f11069f5776

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    gbbib (0.1.2)
+    gbbib (0.1.4)
       cnccs
       iso-bib-item
 

data/lib/gbbib/gb_bibliography.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'gbbib/workers_pool'
+
 # GB bib module.
 module Gbbib
   # GB entry point class.
@@ -7,7 +9,7 @@ module Gbbib
     class << self
       # rubocop:disable Metrics/MethodLength
       # @param text [Strin] code of standard for search
-      # @return [Gbbib::Hits]
+      # @return [Gbbib::HitCollection]
       def search(text)
         if text.match?(/^(GB|GJ|GS)/)
           # Scrape national standards.
@@ -30,6 +32,124 @@ module Gbbib
         end
       end
       # rubocop:enable Metrics/MethodLength
+
+      # @param code [String] the GB standard Code to look up (e..g "GB/T 20223")
+      # @param year [String] the year the standard was published (optional)
+      # @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, opts)
+        return iev.to_xml if code.casecmp? 'IEV'
+        code += '.1' if opts[:all_parts]
+        ret = get1(code, year, opts)
+        return nil if ret.nil?
+        ret.to_most_recent_reference unless year
+        ret.to_all_parts if opts[:all_parts]
+        ret.to_xml
+      end
+
+      private
+
+      def fetch_ref_err(code, year, missed_years)
+        id = year ? "#{code}:#{year}" : code
+        warn "WARNING: no match found on the ISO website for #{id}. "\
+          "The code must be exactly like it is on the website."
+        warn "(There was no match for #{year}, though there were matches "\
+          "found for #{missed_years.join(', ')}.)" unless missed_years.empty?
+        if /\d-\d/.match? code
+          warn "The provided document part may not exist, or the document "\
+            "may no longer be published in parts."
+        else
+          warn "If you wanted to cite all document parts for the reference, "\
+            "use \"#{code} (all parts)\".\nIf the document is not a standard, "\
+            "use its document type abbreviation (TS, TR, PAS, Guide)."
+        end
+        nil
+      end
+
+      def get1(code, year, opts)
+        return iev if code.casecmp? "IEV"
+        result = search_filter(code) or return nil
+        ret = results_filter(result, year)
+        return ret[:ret] if ret[:ret]
+        fetch_ref_err(code, year, ret[:years])
+      end
+
+      def search_filter(code)
+        docidrx = %r{^[^\s]+\s[\d\.]+}
+        # corrigrx = %r{^[^\s]+\s[\d\.]+-[0-9]+/}
+        warn "fetching #{code}..."
+        result = search(code)
+        ret = result.select do |hit|
+          hit.title && hit.title.match(docidrx).to_s == code # &&
+            # !corrigrx.match?(hit.title)
+        end
+        return ret unless ret.empty?
+        []
+      end
+
+      # Sort through the results from Isobib, fetching them three at a time,
+      # and return the first result that matches the code,
+      # matches the year (if provided), and which # has a title (amendments do not).
+      # Only expects the first page of results to be populated.
+      # Does not match corrigenda etc (e.g. ISO 3166-1:2006/Cor 1:2007)
+      # If no match, returns any years which caused mismatch, for error reporting
+      def 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|
+            return { ret: r } if !year
+            r.dates.select { |d| d.type == "published" }.each do |d|
+              return { ret: r } if year.to_i == d.on.year
+              missed_years << d.on.year
+            end
+          end
+        end
+        { years: missed_years }
+      end
+
+      def fetch_pages(s, n)
+        workers = 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 iev
+        Nokogiri::XML.fragment(<<~"END")
+          <bibitem type="international-standard" id="IEV">
+            <title format="text/plain" language="en" script="Latn">Electropedia: The World's Online Electrotechnical Vocabulary</title>
+            <source type="src">http://www.electropedia.org</source>
+            <docidentifier>IEV</docidentifier>
+            <date type="published"> <on>#{Date.today.year}</on> </date>
+            <contributor>
+              <role type="publisher"/>
+              <organization>
+                <name>International Electrotechnical Commission</name>
+                <abbreviation>IEC</abbreviation>
+                <uri>www.iec.ch</uri>
+              </organization>
+            </contributor>
+            <language>en</language> <language>fr</language>
+            <script>Latn</script>
+            <copyright>
+              <from>#{Date.today.year}</from>
+              <owner>
+                <organization>
+                <name>International Electrotechnical Commission</name>
+                <abbreviation>IEC</abbreviation>
+                <uri>www.iec.ch</uri>
+                </organization>
+              </owner>
+            </copyright>
+            <relation type="updates">
+              <bibitem>
+                <formattedref>IEC 60050</formattedref>
+              </bibitem>
+            </relation>
+          </bibitem>
+        END
+      end
     end
   end
 end

data/lib/gbbib/hit.rb

@@ -43,6 +43,8 @@ module Gbbib
       "@title=\"#{title}\">"
     end
 
+    # @param builder [Nokogiri::XML::Builder]
+    # @param opts [Hash]
     # @return [String]
     def to_xml(builder = nil, opts = {})
       if builder

data/lib/gbbib/hit_collection.rb

@@ -21,25 +21,25 @@ module Gbbib
       @hit_pages = hit_pages
     end
 
-    # @return [Isobib::HitCollection]
-    # def fetch
-    #   workers = WorkersPool.new 4
-    #   workers.worker(&:fetch)
-    #   each do |hit|
-    #     workers << hit
-    #   end
-    #   workers.end
-    #   workers.result
-    #   @fetched = true
-    #   self
-    # end
+    # @return [GbBib::HitCollection]
+    def fetch
+      workers = 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}>"
-    # end
+    def to_s
+      inspect
+    end
+    
+    def inspect
+      "<#{self.class}:#{format('%#.14x', object_id << 1)} @fetched=#{@fetched}>"
+    end
   end
 end

data/lib/gbbib/scrapper.rb

@@ -14,18 +14,19 @@ module Gbbib
     # @return [Hash]
     def scrapped_data(doc, src:)
       {
-        committee: get_committee(doc),
-        docid:     get_docid(doc),
-        titles:    get_titles(doc),
-        type:      get_type(doc),
-        docstatus: get_status(doc),
-        gbtype:    get_gbtype(doc),
-        ccs:       get_ccs(doc),
-        ics:       get_ics(doc),
-        link:    [{ type: 'src', content: src }],
-        dates:     get_dates(doc),
-        language:  ['zh'],
-        script:    ['Hans']
+        committee:    get_committee(doc),
+        docid:        get_docid(doc),
+        titles:       get_titles(doc),
+        contributors: get_contributors(doc),
+        type:         get_type(doc),
+        docstatus:    get_status(doc),
+        gbtype:       get_gbtype(doc),
+        ccs:          get_ccs(doc),
+        ics:          get_ics(doc),
+        link:       [{ type: 'src', content: src }],
+        dates:        get_dates(doc),
+        language:     ['zh'],
+        script:       ['Hans']
       }
     end
     # rubocop:enable Metrics/MethodLength
@@ -35,11 +36,17 @@ module Gbbib
     #   * :project_number [String]
     #   * :part_number [String]
     def get_docid(doc, xpt = '//dt[text()="标准号"]/following-sibling::dd[1]')
-      item_ref = doc.xpath(xpt)
-                    .text.match(/(?<=\s)(\d+)-?((?<=-)\d+|)/)
+      item_ref = doc.xpath(xpt).text.match(/(?<=\s)(\d+)\.?((?<=\.)\d+|)/)
       { project_number: item_ref[1], part_number: item_ref[2] }
     end
 
+    def get_contributors(doc, xpt = '//dt[text()="标准号"]/following-sibling::dd[1]')
+      name = doc.xpath(xpt).text.match(/^[^\s]+/).to_s
+      entity = IsoBibItem::Organization.new name: name, abbreviation: name
+      [{ entity: entity, roles: ['publisher'] }]
+    end
+    
+
     # @param doc [Nokogiri::HTML::Document]
     # @return [Array<Hash>]
     #   * :title_intro [String]

data/lib/gbbib/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Gbbib
-  VERSION = '0.1.3'
+  VERSION = '0.1.4'
 end

data/lib/gbbib/workers_pool.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+# Workers poll.
+class WorkersPool
+  attr_accessor :nb_hits
+
+  def initialize(num_workers = 2)
+    @num_workers = num_workers < 2 ? 2 : num_workers
+    @queue = SizedQueue.new(num_workers * 2)
+    @result = []
+    @nb_hits = 0
+  end
+
+  def worker(&block)
+    @threads = Array.new @num_workers do
+      Thread.new do
+        until (item = @queue.pop) == :END
+          @result << yield(item) if block
+        end
+      end
+    end
+  end
+
+  def result
+    @threads.each(&:join)
+    @result
+  end
+
+  def <<(item)
+    @queue << item
+    self
+  end
+
+  def end
+    @num_workers.times { @queue << :END }
+  end
+
+  def size
+    @result.size
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gbbib
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-07-02 00:00:00.000000000 Z
+date: 2018-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -154,6 +154,7 @@ files:
 - lib/gbbib/sec_scrapper.rb
 - lib/gbbib/t_scrapper.rb
 - lib/gbbib/version.rb
+- lib/gbbib/workers_pool.rb
 - lib/gbbib/yaml/prefixes.yaml
 homepage: https://github.com/riboseinc/gdbib
 licenses:
@@ -175,7 +176,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 2.6.12
 signing_key: 
 specification_version: 4
 summary: 'GdBib: retrieve Chinese GB Standards for bibliographic use using the BibliographicItem