relaton-bsi 1.7.pre1

data/lib/relaton_bsi/scrapper.rb

@@ -0,0 +1,156 @@
+# frozen_string_literal: true
+
+module RelatonBsi
+  # Scrapper.
+  module Scrapper
+    class << self
+      # Parse page.
+      # @param hit [RelatonBsi::Hit]
+      # @return [Hash]
+      def parse_page(hit) # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+        doc = hit.hit_collection.agent.get hit.hit[:url]
+        BsiBibliographicItem.new(
+          fetched: Date.today.to_s,
+          type: "standard",
+          docid: fetch_docid(doc),
+          language: ["en"],
+          script: ["Latn"],
+          title: fetch_titles(doc),
+          # doctype: hit_data[:type],
+          docstatus: fetch_status(doc),
+          ics: fetch_ics(doc),
+          date: fetch_dates(hit),
+          contributor: fetch_contributors(doc),
+          editorialgroup: fetch_editorialgroup(doc),
+          abstract: fetch_abstract(doc),
+          copyright: fetch_copyright(doc, hit),
+          link: fetch_link(HitCollection::DOMAIN + hit.hit[:url]),
+          relation: fetch_relations(doc),
+          place: ["London"]
+        )
+      end
+
+      private
+
+      # @param doc [Mechanize::Page]
+      # @return [Array<RelatonIsobib::Ics>]
+      def fetch_ics(doc)
+        ics = doc.at("//tr[th='ICS']/td").text
+        [RelatonIsoBib::Ics.new(ics)]
+      end
+
+      # Fetch abstracts.
+      # @param doc [Mechanize::Page]
+      # @return [Array<Hash>]
+      def fetch_abstract(doc)
+        content = doc.at("//tr[th='Descriptors']/td")
+        [{ content: content.text, language: "en", script: "Latn", }]
+      end
+
+      # Fetch docid.
+      # @param doc [Mechanize::Page]
+      # @return [Array<Hash>]
+      def fetch_docid(doc)
+        docids = []
+        docid = doc.at("//tr[th[.='Standard Number']]/td").text
+        docids << RelatonBib::DocumentIdentifier.new(type: "BSI", id: docid)
+        isbn = doc.at("//tr[th[.='ISBN']]/td").text
+        docids << RelatonBib::DocumentIdentifier.new(type: "ISBN", id: isbn)
+        docids
+      end
+
+      # Fetch status.
+      # @param doc [Mechanize::Page]
+      # @return [RelatonBib::DocumentStatus, NilClass]
+      def fetch_status(doc)
+        s = doc.at("//tr[th='Status']/td")
+        return unless s
+
+        RelatonBib::DocumentStatus.new(stage: s.text)
+      end
+
+      # Fetch workgroup.
+      # @param doc [Mechanize::Page]
+      # @return [RelatonIsoBib::EditorialGroup]
+      def fetch_editorialgroup(doc)
+        wg = doc.at("//tr[th='Committee']/td")
+        tc = RelatonIsoBib::IsoSubgroup.new name: wg.text
+        RelatonIsoBib::EditorialGroup.new technical_committee: [tc]
+      end
+
+      # Fetch relations.
+      # @param doc [Mechanize::Page]
+      # @return [Array<Hash>]
+      def fetch_relations(doc)
+        doc.xpath("//tr[th='Replaces']/td/a").map do |r|
+          fref = RelatonBib::FormattedRef.new(content: r.text, language: "en", script: "Latn")
+          link = fetch_link r[:href]
+          bibitem = BsiBibliographicItem.new(formattedref: fref, type: "standard", link: link)
+          { type: "complements", bibitem: bibitem }
+        end
+      end
+
+      # Fetch titles.
+      # @param doc [Mechanize::Page]
+      # @return [Array<Hash>]
+      def fetch_titles(doc)
+        te = doc.at("//div[@id='title']/h2").text.strip
+        ttls = RelatonBib::TypedTitleString.from_string te, "en", "Latn"
+        tf = doc.at("//tr[th[.='Title in French']]/td")
+        if tf
+          ttls += RelatonBib::TypedTitleString.from_string tf.text.strip, "fr", "Latn"
+        end
+        tf = doc.at("//tr[th[.='Title in German']]/td")
+        if tf
+          ttls += RelatonBib::TypedTitleString.from_string tf.text.strip, "de", "Latn"
+        end
+        ttls
+      end
+
+      # Fetch dates
+      # @param hit [RelatonBsi:Hit]
+      # @return [Array<Hash>]
+      def fetch_dates(hit)
+        [{ type: "published", on: hit.hit[:date].to_s }]
+      end
+
+      # Fetch contributors
+      # @param doc [Mechanize::Page]
+      # @return [Array<Hash>]
+      def fetch_contributors(doc)
+        contrib = { role: [type: "publisher"] }
+        contrib[:entity] = owner_entity doc
+        [contrib]
+      end
+
+      # Fetch links.
+      # @param url [String]
+      # @return [Array<Hash>]
+      def fetch_link(url)
+        [{ type: "src", content: url }]
+      end
+
+      # Fetch copyright.
+      # @param doc [Mechanize::Page]
+      # @param hit [RelatonBsi::Hit]
+      # @return [Array<Hash>]
+      def fetch_copyright(doc, hit)
+        owner = owner_entity doc
+        from = hit.hit[:date].year.to_s
+        [{ owner: [owner], from: from }]
+      end
+
+      # @param doc [Mechanize::Page]
+      # @return [Hash]
+      def owner_entity(doc)
+        abbrev = doc.at("//tr[th='Publisher']/td").text
+        case abbrev
+        when "BSI"
+          { abbreviation: abbrev, name: "British Standards Institution", url: "https://www.bsigroup.com/" }
+        else
+          { name: abbrev }
+        end
+      end
+    end
+  end
+end

data/lib/relaton_bsi/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module RelatonBsi
+  VERSION = "1.7.pre1"
+end

data/lib/relaton_bsi/xml_parser.rb

@@ -0,0 +1,28 @@
+require "nokogiri"
+
+module RelatonBsi
+  class XMLParser < RelatonIsoBib::XMLParser
+    class << self
+      private
+
+      # Override RelatonBib::XMLParser.item_data method.
+      # @param isoitem [Nokogiri::XML::Element]
+      # @returtn [Hash]
+      def item_data(isoitem)
+        data = super
+        ext = isoitem.at "./ext"
+        return data unless ext
+
+        data[:price_code] = ext.at("./price-code")&.text
+        data[:cen_processing] = ext.at("./cen-processing")&.text
+        data
+      end
+
+      # @param item_hash [Hash]
+      # @return [RelatonBsi::BsiBibliographicItem]
+      def bib_item(item_hash)
+        hash = BsiBibliographicItem.new **item_hash
+      end
+    end
+  end
+end

data/relaton_bsi.gemspec

@@ -0,0 +1,49 @@
+# frozen_string_literal: true
+
+require_relative "lib/relaton_bsi/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "relaton-bsi"
+  spec.version       = RelatonBsi::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "RelatonBsi: retrieve BSI Standards for bibliographic use "\
+                       "using the BibliographicItem model"
+  spec.description   = "RelatonBsi: retrieve BSI Standards for bibliographic use "\
+                       "using the BibliographicItem model"
+  spec.homepage      = "https://github.com/metanorma/relaton-bsi"
+  spec.license       = "BSD-2-Clause"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{\A(?:test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Uncomment to register a new dependency of your gem
+  # spec.add_dependency "example-gem", "~> 1.0"
+
+  # For more information and examples about making a new gem, checkout our
+  # guide at: https://bundler.io/guides/creating_gem.html
+  spec.add_development_dependency "equivalent-xml", "~> 0.6"
+  spec.add_development_dependency "pry-byebug"
+  # spec.add_development_dependency "rake", "~> 13.0"
+  # spec.add_development_dependency "rspec", "~> 3.0"
+  # spec.add_development_dependency "ruby-debug-ide"
+  spec.add_development_dependency "ruby-jing"
+  spec.add_development_dependency "simplecov"
+  spec.add_development_dependency "vcr", "~> 5.0.0"
+  spec.add_development_dependency "webmock"
+
+  spec.add_dependency "mechanize"
+  spec.add_dependency "relaton-iso-bib", "~> 1.7.0"
+end

metadata

@@ -0,0 +1,187 @@
+--- !ruby/object:Gem::Specification
+name: relaton-bsi
+version: !ruby/object:Gem::Version
+  version: 1.7.pre1
+platform: ruby
+authors:
+- Ribose Inc.
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2021-04-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: equivalent-xml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: pry-byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: ruby-jing
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: vcr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.0.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.0.0
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  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-iso-bib
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.7.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.7.0
+description: 'RelatonBsi: retrieve BSI Standards for bibliographic use using the BibliographicItem
+  model'
+email:
+- open.source@ribose.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/rake.yml"
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- Gemfile
+- LICENSE.txt
+- README.adoc
+- Rakefile
+- bin/console
+- bin/rspec
+- bin/setup
+- grammars/basicdoc.rng
+- grammars/biblio.rng
+- grammars/bsi.rng
+- grammars/isodoc.rng
+- grammars/isostandard.rng
+- grammars/reqt.rng
+- lib/relaton_bsi.rb
+- lib/relaton_bsi/bsi_bibliographic_item.rb
+- lib/relaton_bsi/bsi_bibliography.rb
+- lib/relaton_bsi/hash_converter.rb
+- lib/relaton_bsi/hit.rb
+- lib/relaton_bsi/hit_collection.rb
+- lib/relaton_bsi/processor.rb
+- lib/relaton_bsi/scrapper.rb
+- lib/relaton_bsi/version.rb
+- lib/relaton_bsi/xml_parser.rb
+- relaton_bsi.gemspec
+homepage: https://github.com/metanorma/relaton-bsi
+licenses:
+- BSD-2-Clause
+metadata:
+  homepage_uri: https://github.com/metanorma/relaton-bsi
+  source_code_uri: https://github.com/metanorma/relaton-bsi
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.4.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">"
+    - !ruby/object:Gem::Version
+      version: 1.3.1
+requirements: []
+rubygems_version: 3.0.6
+signing_key:
+specification_version: 4
+summary: 'RelatonBsi: retrieve BSI Standards for bibliographic use using the BibliographicItem
+  model'
+test_files: []