relaton 3.0.7 → 3.1.0

data/lib/relaton/cli/util.rb

@@ -0,0 +1,8 @@
+module Relaton
+  module Cli
+    module Util
+      extend Relaton::Bib::Util
+      PROGNAME = "relaton-cli".freeze
+    end
+  end
+end

data/lib/relaton/cli/xml_convertor.rb

@@ -0,0 +1,47 @@
+require "nokogiri"
+require_relative "base_convertor"
+
+module Relaton
+  module Cli
+    class XMLConvertor < Relaton::Cli::BaseConvertor
+      def to_yaml
+        convert_and_write(file_content, :to_yaml)
+      end
+
+      # Convert to YAML
+      #
+      # This interface allow us to convert any XML file to YAML.
+      # It only require us to provide a valid XML file and it can
+      # do converstion using default attributes, but it also allow
+      # us to provide custom options to customize this converstion
+      # process.
+      #
+      # @param file [File] The complete path to a XML file
+      # @param options [Hash] Options as hash key, value pairs.
+      #
+      def self.to_yaml(file, options = {})
+        new(file, options).to_yaml
+      end
+
+      private
+
+      def default_ext
+        "yaml"
+      end
+
+      # @param content [Nokogiri::XML::Document]
+      # @return [Hash]
+      def convert_content(content)
+        if %w[bibitem bibdata].include? content.root.name
+          Bibdata.from_xml(content)
+        else
+          Bibcollection.from_xml(content)
+        end
+      end
+
+      def file_content
+        Nokogiri::XML(File.read(file, encoding: "utf-8"))
+      end
+    end
+  end
+end

data/lib/relaton/cli/xml_to_html_renderer.rb

@@ -0,0 +1,117 @@
+require "nokogiri"
+require "liquid"
+
+module Relaton::Cli
+  class XmlToHtmlRenderer
+    def initialize(liquid_dir: nil, stylesheet: nil)
+      @liquid_dir = liquid_dir
+      @stylesheet = read_file(stylesheet)
+      init_liquid_template_and_filesystem
+    end
+
+    # @param index_xml [String] Relaton XML
+    # @return [String] HTML
+    def render(index_xml)
+      Liquid::Template
+        .parse(template)
+        .render(build_liquid_document(index_xml))
+    end
+
+    def uri_for_extension(uri, extension)
+      uri&.sub(/\.[^.]+$/, ".#{extension}")
+    end
+
+    # Render HTML
+    #
+    # This interface allow us to convert a Relaton XML to HTML
+    # using the specified liquid template and stylesheets. It
+    # also do some minor clean during this conversion.
+    #
+    # @param file [String] Relaton XML
+    # @param options [Hash]
+    # @return [String] HTML
+    def self.render(file, options)
+      new(**options).render(file)
+    end
+
+    private
+
+    attr_reader :stylesheet, :liquid_dir, :template
+
+    def read_file(file)
+      File.read(file, encoding: "utf-8")
+    end
+
+    # rubocop:disable Metrics/MethodLength
+    # @param source [String] Relaton XML
+    def build_liquid_document(source)
+      bibcollection = build_bibcollection(source)
+      hash_to_liquid(
+        depth: 2,
+        css: stylesheet,
+        title: bibcollection.title,
+        date: DateTime.now.to_s,
+        author: bibcollection.author,
+        documents: document_items(bibcollection)
+      )
+    end
+
+    def init_liquid_template_and_filesystem
+      file_system = Liquid::LocalFileSystem.new(liquid_dir)
+      @template = read_file(file_system.full_path("index"))
+
+      Liquid::Template.file_system = file_system
+    end
+
+    # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
+
+    # TODO: This should be recursive, but it's not
+    # @param hash [Hash]
+    # @option hash [Integer] :dept
+    # @option hash [String] :css path to stylesheet file
+    # @option hash [String] :title
+    # @option hash [String] :author
+    # @option hash [Array<Hash>] :documents
+    #
+    # @return [Hash]
+    def hash_to_liquid(hash)
+      hash.map do |key, value|
+        case key
+        when "title"
+          if value.is_a?(Array)
+            title = value.detect { |t| t["type"] == "main" } || value.first
+            v = title ? title["content"] : nil
+          elsif value.is_a?(Hash) then v = value["content"]
+          else v = value
+          end
+        when "docidentifier"
+          did = if value.is_a?(Array)
+                  value.detect { |d| (d["id"] || d["content"]).to_s !~ /^(http|https):\/\// } ||
+                    value.first
+                else value
+                end
+          v = did
+        else v = value
+        end
+        [key.to_s, empty2nil(v)]
+      end.to_h
+    end
+    # rubocop:enable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/MethodLength, Metrics/PerceivedComplexity
+
+    def empty2nil(value)
+      value unless value.is_a?(String) && value.empty? && !value.nil?
+    end
+
+    # @param source [String] Relaton XML
+    # @return [Relaton::Bibcollection]
+    def build_bibcollection(source)
+      Relaton::Bibcollection.from_xml(Nokogiri::XML(source))
+    end
+
+    # @param bibcollection [Relaton::Bibcollection]
+    # @return [Array<Hash>]
+    def document_items(bibcollection)
+      bibcollection.to_h["root"]["items"].map { |item| hash_to_liquid(item) }
+    end
+  end
+end

data/lib/relaton/cli/yaml_convertor.rb

@@ -0,0 +1,102 @@
+require "yaml"
+require_relative "base_convertor"
+require_relative "../bib"
+
+module Relaton
+  module Cli
+    class YAMLConvertor < Relaton::Cli::BaseConvertor
+      def to_xml
+        if writable
+          convert_and_write(file_content, :to_xml)
+        else
+          convert_content(file_content).to_xml date_format: :full, bibdata: true
+        end
+      end
+
+      class << self
+        # Convert to XML
+        #
+        # This interface allow us to convert any YAML file to XML.
+        # It only require us to provide a valid YAML file and it can
+        # do converstion using default attributes, but it also allow
+        # us to provide custom options to customize this converstion
+        # process.
+        #
+        # @param file [File] The complete path to a YAML file
+        # @param options [Hash] Options as hash key, value pairs.
+        #
+        def to_xml(file, options = {})
+          new(file, options).to_xml
+        end
+
+        # @param content [Hash] document in YAML format
+        # @return [RelatonBib::BibliographicItem,
+        #   RelatonIso::IsoBiblioraphicItem]
+        def convert_single_file(content)
+          flavor = content.dig("ext", "flavor") || doctype(content["docidentifier"])
+          if (processor = Relaton::Db::Registry.instance.by_type(flavor))
+            begin
+              processor.from_yaml content.to_yaml
+            rescue RuntimeError
+              Relaton::Bib::Item.from_yaml(content.to_yaml)
+            end
+          else
+            Relaton::Bib::Item.from_yaml(content.to_yaml)
+          end
+        end
+
+        private
+
+        # @param content [Hash]
+        # @return [String]
+        def doctype(docid)
+          did = docid.is_a?(Array) ? docid.fetch(0) : docid
+          return unless did
+
+          did["type"] || did.fetch("content")&.match(/^\w+/)&.to_s
+        end
+      end
+
+      private
+
+      def default_ext
+        "rxl"
+      end
+
+      def file_content
+        date_to_string(YAML.load_file(file))
+      end
+
+      def date_to_string(obj)
+        if obj.is_a? Hash
+          obj.reduce({}) do |memo, (k, v)|
+            memo[k] = date_to_string(v)
+            memo
+          end
+        elsif obj.is_a? Array
+          obj.reduce([]) { |memo, v| memo << date_to_string(v) }
+        else
+          obj.is_a?(Date) ? obj.to_s : obj
+        end
+      end
+
+      def convert_collection(content)
+        if content.has_key?("root")
+          content["root"]["items"] = content["root"]["items"].map do |i|
+            # RelatonBib::HashConverter::hash_to_bib(i)
+            self.class.convert_single_file(i)
+          end
+          Relaton::Bibcollection.new(content["root"])
+        end
+      end
+
+      def xml_content(_raw_file)
+        convert_content(file_content).to_xml(date_format: :full, bibdata: true)
+      end
+
+      def convert_content(content)
+        convert_collection(content) || self.class.convert_single_file(content)
+      end
+    end
+  end
+end

data/lib/relaton/cli.rb

@@ -0,0 +1,103 @@
+require "fileutils"
+require "thor"
+require "thor/hollaback"
+require_relative "cli/util"
+require_relative "cli/command"
+
+module Relaton
+  def self.db(dir = nil)
+    Cli.relaton dir
+  end
+
+  module Cli
+    class RelatonDb
+      include Singleton
+
+      DBCONF = "#{Dir.home}/.relaton/dbpath".freeze
+
+      # @param dir [String, nil]
+      # @return [Relaton::Db]
+      def db(dir)
+        if dir
+          FileUtils.mkdir_p File.dirname(DBCONF)
+          File.write DBCONF, dir, encoding: "UTF-8"
+          @db = Relaton::Db.new dir, nil
+        else
+          @db ||= Relaton::Db.new dbpath, nil
+        end
+      end
+
+      private
+
+      # @return [String] path to DB
+      def dbpath
+        if File.exist?(DBCONF)
+          File.read(DBCONF, encoding: "UTF-8")
+        else "#{Dir.home}/.relaton/cache"
+        end
+      end
+    end
+
+    class << self
+      def version
+        # One gem, one version.
+        puts "relaton => #{Relaton::VERSION}"
+      end
+
+      def start(arguments)
+        Relaton::Cli::Command.start(arguments)
+      end
+
+      # Relaton
+      #
+      # Based on current setup, we need to initiate a Db instance to
+      # register all of it's supported processor backends. To make it
+      # easier we have added it as a class method so we can use this
+      # whenever necessary.
+      #
+      # @param dir [String, nil]
+      # @return [Relaton::Db]
+      def relaton(dir)
+        RelatonDb.instance.db dir
+      end
+
+      # @param content [Nokogiri::XML::Document]
+      # @return [RelatonBib::BibliographicItem,
+      #   RelatonIsoBib::IsoBibliongraphicItem]
+      def parse_xml(doc)
+        doc.remove_namespaces! if doc.respond_to?(:remove_namespaces!)
+        if (proc = Cli.processor(doc))
+          proc.from_xml(doc.to_s)
+        else
+          Relaton::Bib::Item.from_xml(doc.to_s) rescue nil
+        end
+      end
+
+      # @param doc [Nokogiri::XML::Element]
+      # @return [RelatonIso::Processor, RelatonIec::Processor,
+      #   RelatonNist::Processor, RelatonIetf::Processot,
+      #   RelatonItu::Processor, RelatonGb::Processor,
+      #   RelatonOgc::Processor, RelatonCalconnect::Processor]
+      def processor(doc)
+        docid = doc.at "docidentifier"
+        proc = get_proc docid
+        return proc if proc
+
+        Relaton::Db::Registry.instance.by_type(docid&.text&.match(/^\w+/)&.to_s)
+      end
+
+      private
+
+      # @param doc [Nokogiri::XML::Element]
+      # @return [RelatonIso::Processor, RelatonIec::Processor,
+      #   RelatonNist::Processor, RelatonIetf::Processot,
+      #   RelatonItu::Processor, RelatonGb::Processor,
+      #   RelatonOgc::Processor, RelatonCalconnect::Processor]
+      def get_proc(docid)
+        return unless docid && docid[:type]
+
+        Relaton::Db::Registry.instance.by_type(docid[:type])
+      end
+    end
+  end
+end

data/lib/relaton/core/processor.rb

@@ -69,7 +69,7 @@ module Relaton
         pubid_class&.parse(ref)
       rescue ArgumentError, ::Pubid::Errors::Error
         # relaton-bib carries the log facade; core specs load without it.
-        require "relaton/bib"
+require_relative "../bib"
         Relaton::Bib::Util.info "does not parse as this flavor's pubid; " \
                                 "passing the reference to the flavor as " \
                                 "written", "relaton-db", key: ref

data/lib/relaton/core.rb

@@ -1,4 +1,4 @@
-require "relaton/logger"
+require_relative "logger"
 
 module Relaton
   # Registered here as well as in the root entry: flavor files and their

data/lib/relaton/db/registry.rb

@@ -13,7 +13,7 @@ module Relaton
         relaton/oasis relaton/doi relaton/jis relaton/xsf
         relaton/ccsds relaton/etsi relaton/isbn relaton/plateau
         relaton/oiml relaton/jcgm relaton/easc relaton/gost relaton/adobe
-        relaton/iala relaton/evs
+        relaton/iala relaton/evs relaton/sae
       ].freeze
 
       include Singleton

data/lib/relaton/db.rb

@@ -1,4 +1,4 @@
-require "relaton/bib"
+require_relative "bib"
 require "yaml"
 require "net/http"
 require "moxml"

data/lib/relaton/doi/CLAUDE.md

@@ -38,7 +38,7 @@ Key classes in `lib/relaton/doi/`:
 - **RSpec** with `expect` syntax only (monkey patching disabled)
 - **VCR** cassettes in `spec/vcr_cassettes/` record Crossref HTTP responses and are never auto-rerecorded (see root `CLAUDE.md`). Because Crossref rate-limits, **re-record this suite alone** — under parallel `rake spec` it answers 429 and the empty body gets recorded as if it were data.
 - **XML fixtures** in `spec/fixtures/` — expected output XML files. The `read_fixture` helper auto-substitutes today's date into `<fetched>` tags.
-- **equivalent-xml** gem for XML comparison in integration tests
+- **canon** gem for XML comparison in integration tests
 - Integration tests in `spec/relaton/doi_spec.rb` cover 40+ document types via VCR cassettes
 - Unit tests in `spec/relaton/doi/parser_spec.rb` test Parser methods directly with hash inputs
 

data/lib/relaton/doi/parser.rb

@@ -731,7 +731,8 @@ module Relaton
       #
       def parse_relation # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
         rels = included_in_relation
-        @src["relation"].each_with_object(rels) do |(k, v), a|
+        # Crossref leaves the key out of some records (SAE standards).
+        (@src["relation"] || {}).each_with_object(rels) do |(k, v), a|
           type, desc = relation_type k
           Array(v).each do |r|
             rel_item = Crossref.get_by_id r["id"]

data/lib/relaton/doi/processor.rb

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

data/lib/relaton/doi.rb

@@ -1,9 +1,9 @@
 # frozen_string_literal: true
 
-require "relaton/bipm"
-require "relaton/ietf"
-require "relaton/ieee"
-require "relaton/nist"
+require_relative "bipm"
+require_relative "ietf"
+require_relative "ieee"
+require_relative "nist"
 require_relative "version"
 require_relative "doi/util"
 require_relative "doi/parser"

data/lib/relaton/easc/processor.rb

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

data/lib/relaton/easc.rb

@@ -1,8 +1,8 @@
 # frozen_string_literal: true
 
-require "relaton/bib"
-require "relaton/index"
-require "relaton/version"
+require_relative "bib"
+require_relative "index"
+require_relative "version"
 require "pubid"
 
 # Relaton::Easc is the EASC (Евразийский экономический совет /

data/lib/relaton/ecma/data_fetcher.rb

@@ -2,7 +2,7 @@
 
 require "English"
 require "mechanize"
-require "relaton/core"
+require_relative "../core"
 require_relative "../ecma"
 require_relative "parser_common"
 require_relative "page_fetcher"

data/lib/relaton/ecma/processor.rb

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

data/lib/relaton/ecma.rb

@@ -3,8 +3,8 @@
 # (The IANA/IHO/IALA/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/bib"
+require_relative "index"
+require_relative "bib"
 require_relative "version"
 require_relative "ecma/util"
 require_relative "ecma/item_data"

data/lib/relaton/element_finder.rb

@@ -0,0 +1,29 @@
+module Relaton
+  module ElementFinder
+    attr_reader :document
+
+    def find_text(xpath, element = nil)
+      find(xpath, element)&.text
+    end
+
+    def find_html(xpath, element = nil)
+      find(xpath, element)&.inner_html
+    end
+
+    def find(xpath, element = nil)
+      (element || document).at(apply_namespace(xpath))
+    end
+
+    def find_xpath(xpath, element = nil)
+      element&.xpath(apply_namespace(xpath))
+    end
+
+    def apply_namespace(xpath)
+      xpath
+        .gsub(%r{/([a-zA-Z])}, "/xmlns:\\1")
+        .gsub(%r{::([a-zA-Z])}, "::xmlns:\\1")
+        .gsub(%r{\[([a-zA-Z][a-z0-9A-Z@/]* ?=)}, "[xmlns:\\1")
+        .gsub(%r{\[([a-zA-Z][a-z0-9A-Z@/]*\])}, "[xmlns:\\1")
+    end
+  end
+end

data/lib/relaton/etsi/data_fetcher.rb

@@ -1,8 +1,8 @@
 require "yeptris"
 require "date"
 require "mechanize"
-require "relaton/core"
-require "relaton/index"
+require_relative "../core"
+require_relative "../index"
 require_relative "../etsi"
 require_relative "data_parser"
 

data/lib/relaton/etsi/item.rb

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

data/lib/relaton/etsi/processor.rb

@@ -1,4 +1,4 @@
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Etsi
@@ -54,7 +54,7 @@ module Relaton
       # @return [String]
       def grammar_hash
         require "digest/md5" # not loaded by etsi.rb; needed on the cold path
-        require "relaton/version"
+require_relative "../version"
         Digest::MD5.hexdigest Relaton::VERSION
       end
 

data/lib/relaton/etsi.rb

@@ -3,7 +3,7 @@
 require "net/http"
 require "mechanize"
 require "pubid"
-require "relaton/index"
+require_relative "index"
 require_relative "version"
 # require_relative "relaton_etsi/pubid"
 require_relative "etsi/bibitem"

data/lib/relaton/evs/processor.rb

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

data/lib/relaton/evs.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 "evs/util"
 require_relative "evs/model/item"

data/lib/relaton/gb/CLAUDE.md

@@ -44,4 +44,4 @@ GB parses identifiers with `Pubid::Gb::Identifier`. It publishes no index, so it
 
 ## Testing
 
-RSpec with WebMock + VCR (cassettes in `spec/vcr_cassettes/`). Network is blocked via WebMock. SimpleCov and equivalent-xml are loaded via `spec/support/`. No index fixture — GB is scraped, not indexed; `spec/fixtures/` holds XML/YAML round-trip data.
+RSpec with WebMock + VCR (cassettes in `spec/vcr_cassettes/`). Network is blocked via WebMock. SimpleCov and canon are loaded via `spec/support/`. No index fixture — GB is scraped, not indexed; `spec/fixtures/` holds XML/YAML round-trip data.

data/lib/relaton/gb/bibliography.rb

@@ -31,7 +31,7 @@ module Relaton
             TScraper.scrape_page ref
           else
             # Scrape sector standard.
-            require "relaton/gb/sec_scraper"
+require_relative "sec_scraper"
             SecScraper.scrape_page ref
           end
         end

data/lib/relaton/gb/processor.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require "relaton/core/processor"
+require_relative "../core/processor"
 
 module Relaton
   module Gb

data/lib/relaton/gb.rb

@@ -1,7 +1,7 @@
 require "digest/md5"
 require "mechanize"
-require "relaton/core"
-require "relaton/iso"
+require_relative "core"
+require_relative "iso"
 require "cnccs"
 require_relative "version"
 require_relative "gb/util"

data/lib/relaton/gost/processor.rb

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

data/lib/relaton/gost.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::Gost is the GOST (Russian federal standards — Гостстандарт)
 # flavor of the unified relaton gem. Adds typed Ext fields (urn,

data/lib/relaton/iala/processor.rb

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