relaton-ieee 1.2.0

data/lib/relaton_ieee/scrapper.rb

@@ -0,0 +1,154 @@
+module RelatonIeee
+  module Scrapper
+    class << self
+      # rubocop:disable Metrics/MethodLength, Metrics/AbcSize
+
+      # papam hit [Hash]
+      # @return [RelatonOgc::OrcBibliographicItem]
+      def parse_page(hit)
+        doc = Nokogiri::HTML Faraday.get(hit["recordURL"]).body
+        IeeeBibliographicItem.new(
+          fetched: Date.today.to_s,
+          title: fetch_title(hit["recordTitle"]),
+          docid: fetch_docid(hit["recordTitle"]),
+          link: fetch_link(hit["recordURL"]),
+          docstatus: fetch_status(doc),
+          abstract: fetch_abstract(doc),
+          contributor: fetch_contributor(doc),
+          language: ["en"],
+          script: ["Latn"],
+          date: fetch_date(doc),
+          committee: fetch_committee(doc),
+        )
+      end
+      # rubocop:enable Metrics/MethodLength, Metrics/AbcSize
+
+      private
+
+      # @param title [String]
+      # @return [Array<RelatonBib::TypedTitleString>]
+      def fetch_title(title)
+        [
+          RelatonBib::TypedTitleString.new(
+            type: "main", content: title, language: "en", script: "Latn",
+          ),
+        ]
+      end
+
+      # @param title [String]
+      # @return [Array<RelatonBib::DocumentIdentifier>]
+      def fetch_docid(title)
+        /^(?<identifier>\S+)/ =~ title
+        [RelatonBib::DocumentIdentifier.new(id: identifier, type: "IEEE")]
+      end
+
+      # @param url [String]
+      # @return [Array>RelatonBib::TypedUri>]
+      def fetch_link(url)
+        [RelatonBib::TypedUri.new(type: "src", content: url)]
+      end
+
+      # @param doc [Nokogiri::HTML::Document]
+      # @return [RelatonBib::DocumentStatus, NilClass]
+      def fetch_status(doc)
+        stage = doc.at("//td[.='Status']/following-sibling::td/div")
+        return unless stage
+
+        RelatonBib::DocumentStatus.new(stage: stage.text)
+      end
+
+      # @param identifier [String]
+      # @return [String]
+      # def fetch_edition(identifier)
+      #   %r{(?<=r)(?<edition>\d+)$} =~ identifier
+      #   edition
+      # end
+
+      # @param doc [Nokogiri::HTML::Document]
+      # @return [Array<RelatonBib::FormattedString>]
+      def fetch_abstract(doc)
+        content = doc.at("//div[@class='description']")
+        return [] unless content
+
+        [RelatonBib::FormattedString.new(content: content.text, language: "en",
+                                         script: "Latn")]
+      end
+
+      # @param doc [Nokogiri::HTML::Document]
+      # @return [Array<RelatonBib::ContributionInfo>]
+      def fetch_contributor(doc)
+        name = doc.at(
+          "//td[.='IEEE Program Manager']/following-sibling::td/div/a",
+        )
+        return [] unless name
+
+        [personn_contrib(name.text)]
+      end
+
+      # @param name [String]
+      # @return [RelatonBib::ContributionInfo]
+      def personn_contrib(name)
+        fname = RelatonBib::FullName.new(
+          completename: RelatonBib::LocalizedString.new(name),
+        )
+        entity = RelatonBib::Person.new(name: fname)
+        RelatonBib::ContributionInfo.new(
+          entity: entity, role: [type: "author"],
+        )
+      end
+
+      # @param name [String]
+      # @return [RelatonBib::ContributionInfo]
+      # def org_contrib(name)
+      #   entity = RelatonBib::Organization.new(name: name)
+      #   RelatonBib::ContributionInfo.new(
+      #     entity: entity, role: [type: "publisher"],
+      #   )
+      # end
+
+      # rubocop:disable Metrics/MethodLength
+
+      # @param date [Nokogiri::HTML::Document]
+      # @return [Array<RelatonBib::BibliographicDate>]
+      def fetch_date(doc)
+        dates = []
+        issued = doc.at "//td[.='Board Approval']/following-sibling::td/div"
+        if issued
+          dates << RelatonBib::BibliographicDate.new(type: "issued",
+                                                     on: issued.text)
+        end
+        published = doc.at("//td[.='History']/following-sibling::td/div")&.
+          text&.match(/(?<=Published Date:)[\d-]+/)&.to_s
+        if published
+          dates << RelatonBib::BibliographicDate.new(type: "published",
+                                                     on: published)
+        end
+        dates
+      end
+
+      # rubocop:disable Metrics/AbcSize
+
+      # @param doc [Nokogiri::HTML::Document]
+      # @return [Array<RelatonIeee::Committee>]
+      def fetch_committee(doc)
+        committees = []
+        sponsor = doc.at "//td[.='Sponsor Committee']/following-sibling::td/div"
+        if sponsor
+          committees << Committee.new(type: "sponsor", name: sponsor.text)
+        end
+        working = doc.at "//td[.='Working Group']/following-sibling::td/div"
+        chair = doc.at "//td[.='Working Group Chair']/following-sibling::td/div"
+        if working
+          committees << Committee.new(type: "working", name: working.text,
+                                      chair: chair.text)
+        end
+        society = doc.at "//td[.='Society']/following-sibling::td/div"
+        if society
+          committees << Committee.new(type: "society", name: society.text)
+        end
+        committees
+      end
+      # rubocop:enable Metrics/MethodLength, Metrics/AbcSize
+    end
+  end
+end

data/lib/relaton_ieee/version.rb

@@ -0,0 +1,3 @@
+module RelatonIeee
+  VERSION = "1.2.0".freeze
+end

data/lib/relaton_ieee/xml_parser.rb

@@ -0,0 +1,29 @@
+module RelatonIeee
+  class XMLParser < RelatonBib::XMLParser
+    class << self
+      private
+
+      # Override RelatonBib::XMLParser.item_data method.
+      # @param item [Nokogiri::XML::Element]
+      # @returtn [Hash]
+      def item_data(item)
+        data = super
+        ext = item.at "./ext"
+        return data unless ext
+
+        data[:committee] = ext.xpath("./committee").map do |c|
+          Committee.new(
+            type: c[:type], name: c.at("name").text, chair: c.at("chair")&.text,
+          )
+        end
+        data
+      end
+
+      # @param item_hash [Hash]
+      # @return [RelatonIeee::IeeeBibliographicItem]
+      def bib_item(item_hash)
+        IeeeBibliographicItem.new item_hash
+      end
+    end
+  end
+end

data/relaton_ieee.gemspec

@@ -0,0 +1,47 @@
+# frozen_string_literal: true
+
+require_relative "lib/relaton_ieee/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "relaton-ieee"
+  spec.version       = RelatonIeee::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "RelatonIeee: retrieve IEEE Standards for bibliographic "\
+                       "use using the IeeeBibliographicItem model"
+  spec.description   = "RelatonIeee: retrieve IEEE Standards for bibliographic "\
+                       "use using the IeeeBibliographicItem model"
+  spec.homepage      = "https://github.com/relaton/relaton-ieee"
+  spec.license       = "BSD-2-Clause"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+
+  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{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "debase"
+  spec.add_development_dependency "equivalent-xml", "~> 0.6"
+  spec.add_development_dependency "pry-byebug"
+  spec.add_development_dependency "rake", "~> 10.0"
+  # 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"
+  spec.add_development_dependency "webmock"
+
+  spec.add_dependency "faraday", "~> 1.0.0"
+  spec.add_dependency "relaton-bib", "~> 1.2.0"
+end

metadata

@@ -0,0 +1,216 @@
+--- !ruby/object:Gem::Specification
+name: relaton-ieee
+version: !ruby/object:Gem::Version
+  version: 1.2.0
+platform: ruby
+authors:
+- Ribose Inc.
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2020-06-26 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: debase
+  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: 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: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: ruby-debug-ide
+  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: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '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: faraday
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+- !ruby/object:Gem::Dependency
+  name: relaton-bib
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.2.0
+description: 'RelatonIeee: retrieve IEEE Standards for bibliographic use using the
+  IeeeBibliographicItem model'
+email:
+- open.source@ribose.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/macos.yml"
+- ".github/workflows/ubuntu.yml"
+- ".github/workflows/windows.yml"
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- Gemfile
+- LICENSE.txt
+- README.adoc
+- Rakefile
+- bin/console
+- bin/rspec
+- bin/setup
+- grammars/basicdoc.rng
+- grammars/biblio.rng
+- grammars/isodoc.rng
+- grammars/reqt.rng
+- lib/relaton_ieee.rb
+- lib/relaton_ieee/committee.rb
+- lib/relaton_ieee/hash_converter.rb
+- lib/relaton_ieee/hit.rb
+- lib/relaton_ieee/hit_collection.rb
+- lib/relaton_ieee/ieee_bibliographic_item.rb
+- lib/relaton_ieee/ieee_bibliography.rb
+- lib/relaton_ieee/processor.rb
+- lib/relaton_ieee/scrapper.rb
+- lib/relaton_ieee/version.rb
+- lib/relaton_ieee/xml_parser.rb
+- relaton_ieee.gemspec
+homepage: https://github.com/relaton/relaton-ieee
+licenses:
+- BSD-2-Clause
+metadata:
+  homepage_uri: https://github.com/relaton/relaton-ieee
+  source_code_uri: https://github.com/relaton/relaton-ieee
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.6
+signing_key: 
+specification_version: 4
+summary: 'RelatonIeee: retrieve IEEE Standards for bibliographic use using the IeeeBibliographicItem
+  model'
+test_files: []