relaton 3.0.7 → 3.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e5d527c7af0e73aafd66151377b063b5dee1aabc862847f463a3e2e6064851fa
-  data.tar.gz: c07269ae1bf1b52ec8d5c6cf9e1ab3e697328327df7b4b125e0b2db70241d5ef
+  metadata.gz: 0bdb2921b9e783bd265ac5fa7fdcf74e464624cc817f3a321e4206602ba94fcf
+  data.tar.gz: 5a329642cc5ed894e9008011cb99a7f35c49c9da624b19b87dbf53d12259325f
 SHA512:
-  metadata.gz: 6a602b0c6e67dfdb52ba5778ca98fd5370c9f54d9f53f649d235a16a19e40130c093bf1104d11c7bf0b9ca10b0872c3a7eee14e1706058da4ddc9e24ed9ac36f
-  data.tar.gz: 2ed59dd8053ee02f22f5fc4adcba23dcc472779d78535bb41ce7fa79b591c8a792ffd9e5033b4779a8e71dbeae3a0ba450c5196fd2738f5fca2d7bba7e7bac48
+  metadata.gz: 9828c92364edaca6d9f56655f8e67aa0de7bdf221a2fdaf03d9fb185a8eb448337dc9f77af028133a390c392c14a273fa31b32e8ab8c00ff1b80813a58efcf9a
+  data.tar.gz: 05a358f667af4b048fb3503d8208c1ff60796b785719da720e1039160c66eaff3c58dc43dbda270d2171197f3636166a32bdc944682435c6d6ed4f63e393a1f8

data/bin/relaton

@@ -0,0 +1,20 @@
+#!/usr/bin/env ruby
+# encoding: UTF-8
+
+# resolve bin path, ignoring symlinks
+require "pathname"
+bin_file = Pathname.new(__FILE__).realpath
+
+# add self to libpath
+$:.unshift File.expand_path("../../lib", bin_file)
+
+# Fixes https://github.com/rubygems/rubygems/issues/1420
+require "rubygems/specification"
+
+class Gem::Specification
+  def this; self; end
+end
+
+require "relaton-cli"
+
+Relaton::Cli.start(ARGV)

data/lib/relaton/3gpp/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module ThreeGpp

data/lib/relaton/3gpp.rb

@@ -3,9 +3,9 @@ require "net/http"
 # index code names. Processor#remove_index_file names no pubid class: the
 # delete never reads the index (see lib/relaton/index/CLAUDE.md).
 require "pubid"
-require "relaton/index"
-require "relaton/core"
-require "relaton/bib"
+require_relative "index"
+require_relative "core"
+require_relative "bib"
 require_relative "version"
 require_relative "3gpp/util"
 require_relative "3gpp/item"

data/lib/relaton/adobe/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Adobe

data/lib/relaton/adobe.rb

@@ -1,9 +1,9 @@
 # frozen_string_literal: true
 
-require "relaton/bib"
-require "relaton/index"
+require_relative "bib"
+require_relative "index"
 require "pubid"
-require "relaton/version"
+require_relative "version"
 
 # Relaton::Adobe is the Adobe (font tech notes, character collections,
 # PostScript Language, etc.) flavor of the unified relaton gem. Adds

data/lib/relaton/bib/item_data.rb

@@ -173,13 +173,13 @@ module Relaton
       # ISO 690 rendered reference (the style instance lives in the
       # relaton-models citation module; the engine in relaton-render).
       def to_iso690(lang: "en", script: "Latn")
-        require "relaton/render/iso690"
+require_relative "../render/iso690"
         Render::Iso690::Renderer.render(self, lang: lang, script: script)
       end
 
       # ISO 690 name-and-date in-text citation.
       def to_iso690_citation(lang: "en", script: "Latn", disambiguator: nil)
-        require "relaton/render/iso690"
+require_relative "../render/iso690"
         Render::Iso690::Renderer.citation(
           self, disambiguator: disambiguator, lang: lang, script: script
         )

data/lib/relaton/bib/model/docidentifier.rb

@@ -66,7 +66,7 @@ module Relaton
         "BSI" => :Bsi,
       }.freeze
 
-      FORMS = %i[external internal].freeze
+      FORMS = %i[external internal slug].freeze
 
       # The parsed identifier. A pubid-backed flavor subclass overrides it.
       def pubid; end
@@ -94,7 +94,22 @@ module Relaton
       def form_content(form)
         flavor = FORM_PUBID[type]
         id = flavor && (pubid || parse_form_pubid(flavor))
-        id ? id.to_s(with_publisher: form == :external) : content
+        return content unless id
+
+        return slug_form(id) if form == :slug
+
+        id.to_s(with_publisher: form == :external)
+      end
+
+      # The pubid-scheme slug (relaton#441): the URN in HTTP-path
+      # clothes, bijective with Pubid.from_slug. A flavor whose
+      # pubid-scheme schema has not landed yet degrades to the stored
+      # content, like a form pubid cannot parse.
+      def slug_form(id)
+        require "pubid"
+        ::Pubid.to_slug(id)
+      rescue ::Pubid::Errors::InvalidInputError, NameError
+        content
       end
 
       def parse_form_pubid(flavor)

data/lib/relaton/bib.rb

@@ -1,10 +1,10 @@
-require "relaton/logger"
+require_relative "logger"
 require "forwardable"
 # require "htmlentities"
 require "bibtex"
 require "iso639"
 require "rfcxml"
-require "relaton/core"
+require_relative "core"
 require "yeptris"
 require_relative "version"
 require_relative "bib/util"

data/lib/relaton/bibcollection.rb

@@ -0,0 +1,146 @@
+require_relative "element_finder"
+
+module Relaton
+  class Bibcollection
+    extend Relaton::ElementFinder
+
+    ATTRIBS = %i[title items doctype author].freeze
+
+    attr_accessor(*ATTRIBS)
+
+    # @param options [Hash]
+    def initialize(options)
+      ATTRIBS.each do |k|
+        value = options[k] || options[k.to_s]
+        send("#{k}=", value)
+      end
+      reduce_items
+    end
+
+    # arbitrary number, must sort after all bib items
+    def doc_number
+      9999999
+    end
+
+    # Add a dcoument to the collection
+    # @param item [RelatonBib::BibliographicItem]
+    def <<(item)
+      items << new_bib_item_class(item)
+    end
+
+    # rubocop:disable Metrics/MethodLength
+
+    # @param source [Nokogiri::XML::Element]
+    def self.from_xml(source)
+      title = find_html("./relaton-collection/title", source)
+      author = find_html(
+        "./relaton-collection/contributor[role/@type='author']/organization/"\
+        "name", source
+      )
+
+      items = find_xpath("./relaton-collection/relation", source)&.map do |item|
+        bibdata = find("./bibdata|./bibitem", item)
+        klass = bibdata ? Bibdata : Bibcollection
+        klass.from_xml(bibdata || item)
+      end
+
+      new(title: title, author: author, items: items)
+    end
+
+    # rubocop:disable Metrics/AbcSize
+
+    # @param opts [Hash]
+    # @return [String] XML
+    def to_xml(opts = {})
+      items.sort_by! &:doc_number
+
+      collection_type = if doctype
+                          "type=\"#{doctype}\""
+                        else
+                          'xmlns="https://open.ribose.com/relaton-xml"'
+                        end
+
+      ret = "<relaton-collection #{collection_type}>"
+      ret += "<title>#{xml_escape(title)}</title>" if title
+      if author
+        ret += "<contributor><role type='author'/><organization><name>"\
+        "#{xml_escape(author)}</name></organization></contributor>"
+      end
+      unless items.empty?
+        items.each do |item|
+          ret += "<relation type='partOf'>"
+          ret += item.to_xml(opts)
+          ret += "</relation>\n"
+        end
+      end
+      ret += "</relaton-collection>\n"
+    end
+    # rubocop:enable Metrics/AbcSize
+
+    # @param item [Hash, RelatonBib::BibliographicItem, Relatin::Bibdata,
+    #   Relaton::Bibcollection]
+    # @return [Relaton::Bibdata, Relaton::Bibcollection]
+    def new_bib_item_class(item)
+      if item.is_a?(Hash)
+        if item["items"]
+          ::Relaton::Bibcollection.new(item)
+        else
+          bibitem = ::Relaton::Cli::YAMLConvertor.convert_single_file item
+          ::Relaton::Bibdata.new bibitem
+        end
+      elsif item.is_a?(Relaton::Bibdata) || item.is_a?(Relaton::Bibcollection)
+        item
+      else ::Relaton::Bibdata.new(item)
+      end
+    end
+    # rubocop:enable Metrics/MethodLength
+
+    def items_flattened
+      items.sort_by! &:doc_number
+
+      items.reduce([]) do |acc, item|
+        acc << if item.is_a? ::Relaton::Bibcollection
+                 item.items_flattened
+               else
+                 item
+               end
+      end
+    end
+
+    def to_yaml
+      to_h.to_yaml
+    end
+
+    def to_h
+      items.sort_by! &:doc_number
+
+      a = ATTRIBS.reduce({}) do |acc, k|
+        acc[k.to_s] = send(k)
+        acc
+      end
+
+      a["items"] = a["items"].map(&:to_h)
+
+      { "root" => a }
+    end
+
+    private
+
+    def reduce_items
+      self.items = (items || []).reduce([]) do |acc, item|
+        acc << if item.is_a?(Bibcollection) || item.is_a?(Bibdata)
+                 item
+               else new_bib_item_class(item)
+               end
+      end
+    end
+
+    # Escape bare & in content for XML serialization, leaving already-encoded
+    # entity references (&amp;, &#123;, &#x1f;) and inline markup (<em> etc.)
+    # untouched. This prevents invalid XML when plain-text values (e.g. from
+    # YAML) contain literal ampersands.
+    def xml_escape(str)
+      str.gsub(/&(?![a-zA-Z][a-zA-Z0-9]*;|#[0-9]+;|#x[0-9a-fA-F]+;)/, "&amp;")
+    end
+  end
+end

data/lib/relaton/bibdata.rb

@@ -0,0 +1,92 @@
+require "date"
+
+module Relaton
+  class Bibdata
+    URL_TYPES = %i[uri xml pdf doc html rxl txt].freeze
+
+    # @return [RelatonBib::BibliographicItem]
+    attr_reader :bibitem
+
+    # @param bibitem [RelatonBib::BibliographicItem]
+    def initialize(bibitem)
+      @bibitem = bibitem
+    end
+
+    def docidentifier
+      @bibitem.docidentifier.first&.content&.to_s
+    end
+
+    # def doctype
+    #   @bibitem.type
+    # end
+
+    # From http://gavinmiller.io/2016/creating-a-secure-sanitization-function/
+    FILENAME_BAD_CHARS = ["/", '\\', "?", "%", "*", ":", "|", '"', "<", ">",
+                          ".", " "].freeze
+
+    def docidentifier_code
+      return "" if docidentifier.nil?
+
+      FILENAME_BAD_CHARS.reduce(docidentifier.downcase) do |result, bad_char|
+        result.gsub(bad_char, "-")
+      end
+    end
+
+    DOC_NUMBER_REGEX = /([\w\/]+)\s+(\d+):?(\d*)/.freeze
+    def doc_number
+      docidentifier&.match(DOC_NUMBER_REGEX) ? $2.to_i : 999999
+    end
+
+    def self.from_xml(source)
+      bi = Relaton::Cli.parse_xml(source)
+      new(bi) if bi
+    end
+
+    def to_xml(opts = {})
+      options = { bibdata: true, date_format: :full }.merge(
+        opts.select { |k, _v| k.is_a? Symbol },
+      )
+      @bibitem.to_xml(**options)
+    end
+
+    def to_h
+      URL_TYPES.each_with_object(YAML.safe_load(@bibitem.to_yaml)) do |t, h|
+        value = send t
+        h[t.to_s] = value if value
+      end
+    end
+
+    def to_yaml
+      to_h.to_yaml
+    end
+
+    # rubocop:disable Metrics/CyclomaticComplexity, Metrics/AbcSize
+    # rubocop:disable Metrics/MethodLength, Metrics/PerceivedComplexity, Style/MissingRespondToMissing
+
+    def method_missing(meth, *args)
+      if @bibitem.respond_to?(meth)
+        @bibitem.send meth, *args
+      elsif URL_TYPES.include? meth
+        source = (@bibitem.source || []).detect do |l|
+          l.type == meth.to_s || (meth == :uri && l.type.nil?)
+        end
+        source&.content&.to_s
+      elsif URL_TYPES.include? meth.match(/^\w+(?==)/).to_s.to_sym
+        /^(?<type>\w+)/ =~ meth
+        @bibitem.source ||= []
+        source = @bibitem.source.detect do |l|
+          l.type == type || (type == "uri" && l.type.nil?)
+        end
+        if source
+          source.content = args[0]
+        else
+          @bibitem.source << Relaton::Bib::Uri.new(type: type, content: args[0])
+        end
+      else
+        super
+      end
+    end
+    # rubocop:enable Metrics/CyclomaticComplexity, Metrics/AbcSize
+    # rubocop:enable Metrics/MethodLength, Metrics/PerceivedComplexity, Style/MissingRespondToMissing
+  end
+end

data/lib/relaton/bipm/data_outcomes_parser.rb

@@ -94,9 +94,14 @@ module Relaton::Bipm
         @data_fetcher.write_file path, has_part_item, warn_duplicate: false
         path = File.join dir, "#{num}-#{part}.#{@data_fetcher.ext}"
       elsif part
-        hash[:title].each { |t| t.content.sub!(/\s\(.+\)$/, "") }
+        # The part item keeps the full titles ("… (Session I)"); the base
+        # item's titles drop the parenthetical. Assign the stripped form -
+        # `Title#content` exposes the source metadata string, and a
+        # mutating `sub!` would strip the part item's title too (the two
+        # share the string object).
         h = meeting_bibitem body: body, type: type, en: en_md, fr: fr_md, num: num, src: src, pdf: en["pdf"]
         add_part h, body, type, num, part
+        hash[:title].each { |t| t.content = t.content.sub(/\s\(.+\)$/, "") }
         part_item = ItemData.new(**h)
         part_item_path = File.join dir, "#{num}-#{part}.#{@data_fetcher.ext}"
         @data_fetcher.write_file part_item_path, part_item

data/lib/relaton/bipm/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Bipm

data/lib/relaton/bipm.rb

@@ -1,8 +1,8 @@
 require "zip"
 require "fileutils"
-require "relaton/bib"
-require "relaton/index"
-require "relaton/core"
+require_relative "bib"
+require_relative "index"
+require_relative "core"
 require "pubid"
 require_relative "version"
 require_relative "bipm/util"

data/lib/relaton/bsi/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton::Bsi
   class Processor < Relaton::Core::Processor

data/lib/relaton/bsi.rb

@@ -1,4 +1,4 @@
-require "relaton/iso"
+require_relative "iso"
 require_relative "version"
 require_relative "bsi/util"
 require_relative "bsi/item_data"

data/lib/relaton/calconnect/data_fetcher.rb

@@ -2,8 +2,8 @@ require "yeptris"
 # frozen_string_literal:true
 
 require "mechanize"
-require "relaton/core"
-require "relaton/index"
+require_relative "../core"
+require_relative "../index"
 # The flavor top-level, for INDEXFILE and ::Pubid::Calconnect::Identifier.
 # `relaton-data-calconnect`'s crawler requires THIS file and nothing else, so
 # without it `#index` NameErrors on the very first document. (The ECMA form;

data/lib/relaton/calconnect/model/item.rb

@@ -1,4 +1,4 @@
-require "relaton/bib"
+require_relative "../../bib"
 require_relative "../item_data"
 require_relative "../docidentifier"
 require_relative "ext"

data/lib/relaton/calconnect/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton::Calconnect
   class Processor < Relaton::Core::Processor

data/lib/relaton/calconnect.rb

@@ -3,8 +3,8 @@
 # (The ECMA/IANA/IHO/OGC form; spec/relaton/lazy_loading_spec.rb guards that
 # this file is not itself loaded when a Db is built.)
 require "pubid"
-require "relaton/index"
-require "relaton/core"
+require_relative "index"
+require_relative "core"
 require_relative "version"
 require_relative "calconnect/model/item"
 require_relative "calconnect/util"

data/lib/relaton/ccsds/data/fetcher.rb

@@ -1,7 +1,7 @@
 require "yeptris"
 require "json"
 require "mechanize"
-require "relaton/index"
+require_relative "../../index"
 require "pubid"
 require_relative "../../ccsds"
 require_relative "parser"

data/lib/relaton/ccsds/model/item.rb

@@ -1,4 +1,4 @@
-require "relaton/bib"
+require_relative "../../bib"
 require_relative "../item_data"
 require_relative "docidentifier"
 require_relative "ext"

data/lib/relaton/ccsds/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Ccsds

data/lib/relaton/ccsds/util.rb

@@ -1,4 +1,4 @@
-require "relaton/bib/util"
+require_relative "../bib/util"
 
 module Relaton
   module Ccsds

data/lib/relaton/ccsds.rb

@@ -3,7 +3,7 @@
 # require "mechanize"
 # require "relaton/core"
 # require "relaton/bib"
-require "relaton/index"
+require_relative "index"
 require "pubid"
 require_relative "version"
 # require_relative "ccsds/processor"

data/lib/relaton/cen/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Cen

data/lib/relaton/cen.rb

@@ -2,10 +2,10 @@
 
 require "digest/md5"
 require "mechanize"
-require "relaton/core"
+require_relative "core"
 require "isoics"
 require "pubid"
-require "relaton/bib"
+require_relative "bib"
 require_relative "version"
 require_relative "cen/util"
 require_relative "cen/model/item"

data/lib/relaton/cie/data_fetcher.rb

@@ -5,9 +5,9 @@ require "fileutils"
 require "ferrum"
 require "moxml"
 require "pubid"
-require "relaton/index"
-require "relaton/bib"
-require "relaton/core/data_fetcher"
+require_relative "../index"
+require_relative "../bib"
+require_relative "../core/data_fetcher"
 require_relative "../cie"
 
 module Relaton

data/lib/relaton/cie/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Cie

data/lib/relaton/cie.rb

@@ -1,8 +1,8 @@
 require "moxml"
 # require "parslet"
 require "pubid"
-require "relaton/index"
-require "relaton/bib"
+require_relative "index"
+require_relative "bib"
 # require "relaton_bib/name_parser"
 require_relative "version"
 require_relative "cie/authors_parser"