relaton-ietf 1.9.9 → 1.9.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b877d9712043836edc2a8bfc4fed64e403c2df5d413110620f4d16d5d8edc47c
-  data.tar.gz: 432049ec32a601221c1c82601d2ec9a6d2287e1068fa31c5495f4255063ac26a
+  metadata.gz: 7b66f8a6c856c44ac8b16ab20f9efe24f1c87e3087afd02870938e38cf28d76a
+  data.tar.gz: 8ea240983edf3b80fec6de69de1845d80e318fbd12a724e13d56c6b7901c2deb
 SHA512:
-  metadata.gz: 6d63daffca42a241bd32bd896abacc0747c49b1ca3512ab7842e5655d692d6610b7c62de8834853fc66939b367b12fc8b3e73585a9f37a373cae0df83adf53b7
-  data.tar.gz: 797e01b58acd21ce291357a2baaa989bd7fc6e7ac5bc084b10c4a1cc94b06425c5ba98c2e96812190c8b37c0a6a73f20f25670efa8c72b1de92fd0491cf4af7a
+  metadata.gz: aaed3229833cb24cc7694ee1ac5d817097905c1e520ff8e24e15fbb43ef615548eafb646e992f255cbb7492319ceae139457df8992e143b1ca5c248bb8d6982d
+  data.tar.gz: '08b765ebc09ff7c328f4c8059a33acb559e6e1ebb0bdcd7911ea2d71a8bcece6ef5d0ffbee6120876940a1df04a93a5e67a9ad6edf83305588c4955e7ba66309'

data/.gitignore

@@ -6,6 +6,7 @@
 /pkg/
 /spec/reports/
 /tmp/
+/bibxml-ids/
 .vscode/
 
 # rspec failure tracking

data/README.adoc

@@ -138,7 +138,7 @@ RelatonIetf::IetfBibliographicItem.from_hash hash
 There is a IETF datasets what can be converted into RelatonXML/BibXML/BibYAML formats:
 
 - `ietf-rfcsubseries` - https://www.rfc-editor.org/rfc-index.xml (`<bcp-entry>`, `<fyi-entry>`, `<std-entry>`)
-- `ietf-internet-drafts` - https://www.ietf.org/lib/dt/sprint/bibxml-ids.tgz
+- `ietf-internet-drafts` - converts files from local directory `./bibxml-ids`. Use `rsync -avcizxL rsync.ietf.org::bibxml-ids ./bibxml-ids` command to fetch the files.
 - `ietf-rfc-entries` - https://www.rfc-editor.org/rfc-index.xml (`<rfc-entry>`)
 
 The method `RelatonIetf::DataFetcher.fetch(source, output: "data", format: "yaml")` converts all the documents from the dataset and save them to the `./data` folder in YAML format.

data/lib/relaton_ietf/data_fetcher.rb

@@ -1,6 +1,6 @@
-require "rubygems"
-require "rubygems/package"
-require "zlib"
+# require "rubygems"
+# require "rubygems/package"
+# require "zlib"
 require "relaton_ietf/rfc_index_entry"
 require "relaton_ietf/rfc_entry"
 
@@ -64,22 +64,28 @@ module RelatonIetf
     # Fetches ietf-internet-drafts documents
     #
     def fetch_ieft_internet_drafts # rubocop:disable Metrics/MethodLength
-      gz = OpenURI.open_uri("https://www.ietf.org/lib/dt/sprint/bibxml-ids.tgz")
-      z = Zlib::GzipReader.new(gz)
-      io = StringIO.new(z.read)
-      z.close
-      Gem::Package::TarReader.new io do |tar|
-        tar.each do |tarfile|
-          next if tarfile.directory?
+      # gz = OpenURI.open_uri("https://www.ietf.org/lib/dt/sprint/bibxml-ids.tgz")
+      # z = Zlib::GzipReader.new(gz)
+      # io = StringIO.new(z.read)
+      # z.close
+      # Gem::Package::TarReader.new io do |tar|
+      #   tar.each do |tarfile|
+      #     next if tarfile.directory?
 
-          save_doc RelatonBib::BibXMLParser.parse(tarfile.read)
-        end
+      #     save_doc BibXMLParser.parse(tarfile.read)
+      #   end
+      # end
+      Dir["bibxml-ids/*.xml"].each do |file|
+        save_doc BibXMLParser.parse(File.read(file, encoding: "UTF-8"))
       end
     end
 
     def fetch_ieft_rfcs
       rfc_index.xpath("xmlns:rfc-entry").each do |doc|
         save_doc RfcEntry.parse(doc)
+      rescue StandardError => e
+        warn "Error parsing #{doc.at('./xmlns:doc-id').text}: #{e.message}"
+        warn e.backtrace[0..5].join("\n")
       end
     end
 

data/lib/relaton_ietf/rfc_entry.rb

@@ -41,17 +41,35 @@ module RelatonIetf
         abstract: parse_abstract,
         relation: parse_relation,
         status: parse_status,
+        series: parse_series,
         editorialgroup: parse_editorialgroup,
       )
     end
 
+    #
+    # Parse series
+    #
+    # @return [Array<RelatonBib::Series>] series
+    #
+    def parse_series
+      title = RelatonBib::TypedTitleString.new(content: "RFC")
+      @doc.xpath("./xmlns:is-also/xmlns:doc-id").map do |s|
+        /^(?<name>\D+)(?<num>\d+)/ =~ s.text
+        t = RelatonBib::TypedTitleString.new(content: name)
+        RelatonBib::Series.new title: t, number: num.gsub(/^0+/, "")
+      end + [RelatonBib::Series.new(title: title, number: docnum)]
+    end
+
     #
     # Parse document identifiers
     #
     # @return [Array<RelatonBib::DocumentIdettifier>] document identifiers
     #
     def parse_docid
-      ids = [RelatonBib::DocumentIdentifier.new(id: pub_id, type: "IETF")]
+      ids = [
+        RelatonBib::DocumentIdentifier.new(id: pub_id, type: "IETF"),
+        RelatonBib::DocumentIdentifier.new(id: code, type: "IETF", scope: "anchor"),
+      ]
       doi = @doc.at("./xmlns:doi").text
       ids << RelatonBib::DocumentIdentifier.new(id: doi, type: "DOI")
       ids
@@ -73,7 +91,16 @@ module RelatonIetf
     # @return [String] PubID
     #
     def pub_id
-      "IETF #{code.sub(/^(RFC)(\d+)/, '\1 \2')}"
+      "RFC #{docnum}"
+    end
+
+    #
+    # Parse document number
+    #
+    # @return [String] document number
+    #
+    def docnum
+      /\d+$/.match(code).to_s.sub(/^0+/, "")
     end
 
     #
@@ -115,16 +142,66 @@ module RelatonIetf
     #
     # @return [Array<RelatonBib::ContributionInfo>] document contributors
     #
-    def parse_contributor
-      @doc.xpath("./xmlns:author").map do |contributor|
+    def parse_contributor # rubocop:disable Metrics/MethodLength, Metrics/AbcSize, Metrics/CyclomaticComplexity
+      @doc.xpath("./xmlns:author").map do |contributor| # rubocop:disable Metrics/BlockLength
         n = contributor.at("./xmlns:name").text
-        name = RelatonBib::LocalizedString.new( n,  "en",  "Latn")
-        fname = RelatonBib::FullName.new(completename: name)
-        person = RelatonBib::Person.new(name: fname)
-        RelatonBib::ContributionInfo.new(entity: person, role: [{ type: "author" }])
+        case n
+        when "ISO"
+          entity = RelatonBib::Organization.new(abbrev: n, name: "International Organization for Standardization")
+        when "International Organization for Standardization"
+          entity = RelatonBib::Organization.new(abbrev: "ISO", name: n)
+        when "IAB"
+          entity = RelatonBib::Organization.new(abbrev: n, name: "Internet Architecture Board")
+        when "IESG"
+          entity = RelatonBib::Organization.new(abbrev: n, name: "Internet Engineering Steering Group")
+        when "Internet Engineering Steering Group", "Federal Networking Council", "Internet Architecture Board",
+          "Internet Activities Board", "Defense Advanced Research Projects Agency", "National Science Foundation",
+          "National Research Council", "National Bureau of Standards"
+          abbr = n.split.map { |w| w[0] if w[0] == w[0].upcase }.join
+          entity = RelatonBib::Organization.new(abbrev: abbr, name: n)
+        when "IETF Secretariat"
+          entity = RelatonBib::Organization.new(abbrev: "IETF", name: n)
+        when "Audio-Video Transport Working Group", /North American Directory Forum/, "EARN Staff",
+          "Vietnamese Standardization Working Group", "ACM SIGUCCS", "ESCC X.500/X.400 Task Force",
+          "Sun Microsystems", "NetBIOS Working Group in the Defense Advanced Research Projects Agency",
+          "End-to-End Services Task Force", "Network Technical Advisory Group", "Bolt Beranek",
+          "Newman Laboratories", "Gateway Algorithms and Data Structures Task Force",
+          "Network Information Center. Stanford Research Institute", "RFC Editor",
+          "Information Sciences Institute University of Southern California"
+          entity = RelatonBib::Organization.new(name: n)
+        when "Internet Assigned Numbers Authority (IANA)"
+          entity = RelatonBib::Organization.new(abbrev: "IANA", name: "Internet Assigned Numbers Authority")
+        when "ESnet Site Coordinating Comittee (ESCC)"
+          entity = RelatonBib::Organization.new(abbrev: "ESCC", name: "ESnet Site Coordinating Comittee")
+        when "Energy Sciences Network (ESnet)"
+          entity = RelatonBib::Organization.new(abbrev: "ESnet", name: "Energy Sciences Network")
+        when "International Telegraph and Telephone Consultative Committee of the International Telecommunication Union"
+          entity = RelatonBib::Organization.new(abbrev: "CCITT", name: n)
+        else
+          # int, snm = n.split
+          /^(?:(?<int>(?:\p{Lu}+(?:-\w|\(\w\))?\.{0,2}[-\s]?)+)\s)?(?<snm>[[:alnum:]\s'-.]+)$/ =~ n
+          surname = RelatonBib::LocalizedString.new(snm, "en", "Latn")
+          name = RelatonBib::LocalizedString.new(n, "en", "Latn")
+          fname = RelatonBib::FullName.new(completename: name, initial: initials(int), surname: surname)
+          entity = RelatonBib::Person.new(name: fname)
+        end
+        RelatonBib::ContributionInfo.new(entity: entity, role: [{ type: "author" }])
       end
     end
 
+    #
+    # Ctreat initials
+    #
+    # @param [String] int
+    #
+    # @return [Array<RelatonBib::LocalizedString>]
+    #
+    def initials(int)
+      return [] unless int
+
+      int.split(/\.-?\s?|\s/).map { |i| RelatonBib::LocalizedString.new i, "en", "Latn" }
+    end
+
     #
     # Parse document keywords
     #
@@ -141,7 +218,10 @@ module RelatonIetf
     #
     def parse_abstract
       @doc.xpath("./xmlns:abstract").map do |c|
-        RelatonBib::FormattedString.new(content: c.text, language: "en",
+        content = c.xpath("./xmlns:p").map do |p|
+          "<#{p.name}>#{p.text.strip}</#{p.name}>"
+        end.join
+        RelatonBib::FormattedString.new(content: content, language: "en",
                                         script: "Latn", format: "text/html")
       end
     end

data/lib/relaton_ietf/rfc_index_entry.rb

@@ -19,7 +19,7 @@ module RelatonIetf
     #
     # @param [Nokogiri::XML::Element] doc document
     #
-    # @return [RelatonIetf:RfcIndexEntry, nil]
+    # @return [RelatonIetf:IetfBibliographicItem, nil]
     #
     def self.parse(doc)
       doc_id = doc.at("./xmlns:doc-id")
@@ -54,13 +54,14 @@ module RelatonIetf
 
     def parse_docid
       [
-        RelatonBib::DocumentIdentifier.new(type: "IETF", scope: "anchor", id: anchor),
+        RelatonBib::DocumentIdentifier.new(type: "IETF", id: pub_id),
+        RelatonBib::DocumentIdentifier.new(type: "IETF", scope: "anchor", id: @doc_id),
       ]
     end
 
-    # def pub_id
-    #   "IETF #{@name.upcase} #{@shortnum}"
-    # end
+    def pub_id
+      "#{@name.upcase} #{@shortnum}"
+    end
 
     def anchor
       "#{@name.upcase}#{@shortnum}"

data/lib/relaton_ietf/version.rb

@@ -1,3 +1,3 @@
 module RelatonIetf
-  VERSION = "1.9.9".freeze
+  VERSION = "1.9.13".freeze
 end

data/relaton_ietf.gemspec

@@ -38,6 +38,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "vcr"
   spec.add_development_dependency "webmock"
 
-  spec.add_dependency "relaton-bib", ">= 1.9.12"
-  spec.add_dependency "zlib", "~> 1.1.0"
+  spec.add_dependency "relaton-bib", ">= 1.9.19"
+  # spec.add_dependency "zlib", "~> 1.1.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-ietf
 version: !ruby/object:Gem::Version
-  version: 1.9.9
+  version: 1.9.13
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2021-12-28 00:00:00.000000000 Z
+date: 2022-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: equivalent-xml
@@ -128,28 +128,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.9.12
+        version: 1.9.19
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.9.12
-- !ruby/object:Gem::Dependency
-  name: zlib
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.1.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 1.1.0
+        version: 1.9.19
 description: "RelatonIetf: retrieve IETF Standards for bibliographic use \nusing the
   BibliographicItem model.\n\nFormerly known as rfcbib.\n"
 email: