pubid 1.15.19 → 2.0.0.pre.alpha.2

data/lib/pubid/idf/parser.rb

@@ -0,0 +1,143 @@
+# frozen_string_literal: true
+
+require "parslet"
+
+module Pubid
+  module Idf
+    class Parser < Parslet::Parser
+      include ::Pubid::Parser::CommonParseRules
+      include ::Pubid::Parser::CommonParseMethods
+
+      # We need to sort by length to match longest first because that's how Parslet works
+      TYPED_STAGES = Pubid::Idf::Scheme.typed_stages
+        .map(&:abbr).flatten.sort_by(&:length).reverse
+      TYPED_STAGES_SUPPLEMENTS = Pubid::Idf::Scheme.supplement_typed_stages
+        .map(&:abbr).flatten.sort_by(&:length).reverse
+
+      root :identifier
+
+      rule(:identifier) do
+        supplement_identifier |
+          identifier_publisher
+      end
+
+      # IDF 125A:1988
+      rule(:prefix_sole_publisher) do
+        str("IDF").as(:publisher)
+      end
+
+      rule(:number_with_part) do
+        (number >> part_and_subpart.maybe).as(:number_with_part)
+      end
+
+      # IDF identifiers can contain alphanumeric characters
+      # IDF 125A:1988
+      rule(:number) do
+        match('\w').repeat(1, 5)
+      end
+
+      rule(:date) do
+        (year_digits >>
+          (dash >> month_digits).maybe >>
+          (dash >> day_digits).maybe
+        ).as(:date)
+      end
+
+      rule(:part_and_subpart) do
+        # IDF 80-1:2001
+        # the "space?" needed to handle "ISO/TS 10303- 1751:2014"
+        dash >> space? >>
+          # matches a part
+          match('\w').repeat >>
+          # matches a subpart, e.g. "A01" or "1-2" (yes we treat {5}-{1-1} as part and subpart)
+          (dash >> match('\w').repeat).repeat.maybe
+      end
+
+      rule(:all_parts) do
+        str("(all parts)").as(:all_parts)
+      end
+
+      rule(:type_with_stage) do
+        # IDF/RM 82:2004
+        # IDF/RM 254:2022
+        array_to_str(TYPED_STAGES).as(:type_with_stage) >>
+          (match('\d').as(:stage_iteration) >> space).maybe
+      end
+
+      rule(:language) do
+        # IDF/RM 82:2004(en,fr)
+        str("(") >>
+          (
+            # parse 2-char language codes: ru,en,fr,de,ar,es
+            (match["a-z"].repeat(1) >> str(",").maybe) |
+            # parse single language codes: R/E/F
+            (match["EFARDS"] >> str("/").maybe)
+          ).repeat.as(:languages) >>
+          str(")")
+      end
+
+      rule(:stage_iteration) do
+        # "ISO 11243.1"
+        str(".") >> match('\d').as(:stage_iteration)
+      end
+
+      rule(:second_part) do
+        number_with_part >>
+          stage_iteration.maybe >>
+          space? >> (
+            # :2005-02
+            str(":") >> date
+          ).maybe
+      end
+
+      rule(:third_part) do
+        # End of the identifier, we can have language, or all parts
+        space? >> language.maybe >> all_parts.maybe
+      end
+
+      # prefix sole publishers with type and stage
+      # IDF/RM 82:2004
+      rule(:identifier_publisher) do
+        identifier_publisher_no_third >> third_part
+      end
+
+      rule(:identifier_publisher_no_third) do
+        prefix_sole_publisher >> space? >> str("/").maybe >>
+          type_with_stage.maybe >>
+          space.maybe >>
+          second_part
+      end
+
+      rule(:supplement_type_with_stage) do
+        # "AMD" or "COR"
+        array_to_str(TYPED_STAGES_SUPPLEMENTS).as(:type_with_stage)
+      end
+
+      # IDF 148-1:2008 / COR 1:2009
+      # IDF 140-1:2007 / AMD1:2012 (no space between AMD and 1)
+      rule(:supplement_identifier_no_third) do
+        identifier_publisher_no_third.as(:base_identifier) >>
+          space? >> str("/") >> space? >>
+          supplement_type_with_stage >>
+          space.maybe >> second_part
+      end
+
+      rule(:supplement_identifier) do
+        supplement_identifier_no_third >> third_part
+      end
+
+      # # ISO/IEC 13818-1:2015/Amd 3:2016/Cor 1:2017
+      # # ISO/IEC 19794-7:2014/Amd 1:2015/CD Cor 1
+      # rule(:supplement_supplement_identifier) do
+      #   supplement_identifier_no_third.as(:base_identifier) >>
+      #     str("/") >> supplement_type_with_stage >>
+      #     # digits.as(:stage_iteration).maybe >>
+      #     space? >> second_part >> third_part
+      # end
+
+      rule(:dash) do
+        str("-") | str("‑") | str("‐")
+      end
+    end
+  end
+end

data/lib/pubid/idf/scheme.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Idf
+    class Scheme < Pubid::Scheme
+      class << self
+        def identifiers
+          @identifiers ||= [
+            Identifiers::InternationalStandard,
+            Identifiers::ReviewedMethod,
+          ].freeze
+        end
+
+        def supplement_identifiers
+          @supplement_identifiers ||= [
+            Identifiers::Amendment,
+            Identifiers::Corrigendum,
+          ].freeze
+        end
+
+        def typed_stages
+          @typed_stages ||= identifiers.flat_map { |klass| klass::TYPED_STAGES }
+        end
+
+        def supplement_typed_stages
+          @supplement_typed_stages ||= supplement_identifiers.flat_map do |klass|
+            klass::TYPED_STAGES
+          end
+        end
+
+        def locate_typed_stage_by_abbr(abbr)
+          abbr = "" if abbr.nil?
+
+          typed_stage = (typed_stages + supplement_typed_stages).detect do |ts|
+            ts.abbr.include?(abbr)
+          end
+
+          unless typed_stage
+            raise ArgumentError,
+                  "Unknown type abbreviation: '#{abbr}'"
+          end
+
+          typed_stage
+        end
+
+        def locate_identifier_klass_by_type_code(type_code)
+          identifier_klass = (identifiers + supplement_identifiers).detect do |klass|
+            klass.type[:key].to_s == type_code.to_s
+          end
+
+          unless identifier_klass
+            raise ArgumentError,
+                  "Unknown type code: #{type_code}"
+          end
+
+          identifier_klass
+        end
+      end
+    end
+  end
+end

data/lib/pubid/idf/single_identifier.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Idf
+    # Base class for single IDF identifiers (base documents)
+    #
+    # This class provides common attributes for all base document types
+    # like InternationalStandard and ReviewedMethod.
+    #
+    # Supplement identifiers (amendments, corrigenda) should NOT inherit
+    # from this class - they should inherit directly from Identifier.
+    #
+    # Note: The type attribute is inherited from the base Identifier class.
+    # Concrete classes should add their own default value like:
+    #   attribute :type, Components::Type, default: -> { self.class.type[:key] }
+    class SingleIdentifier < Identifier
+    end
+  end
+end

data/lib/pubid/idf/supplement_identifier.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Idf
+    # Base class for supplement identifiers (amendments, corrigenda).
+    #
+    # This class provides common attributes and behavior for all supplement
+    # identifier types. Supplements wrap a base identifier and add additional
+    # information like amendment/corrigendum number and date.
+    #
+    # Supplement identifiers should inherit from this class, not from
+    # SingleIdentifier (which is for base documents only).
+    #
+    # Architecture Note:
+    # - Supplements have a base_identifier attribute (recursive structure)
+    # - Supplements share the to_s rendering pattern
+    # - Supplements inherit typed_stage from base Identifier class
+    class SupplementIdentifier < Identifier
+      attribute :base_identifier, Identifier
+
+      # Render supplement identifier as string.
+      #
+      # Format: "base_identifier/ABBREVIATION number:year"
+      # Example: "IDF 125:1988/AMD 1:2023"
+      #
+      # @param lang [Symbol] Language (default: :en)
+      # @param lang_single [Boolean] Use single-char language codes (default: false)
+      # @param with_edition [Boolean] Include edition (default: false)
+      # @return [String] String representation of supplement
+      def to_s(lang: :en, lang_single: false, with_edition: false)
+        [
+          base_identifier.to_s(lang: lang, lang_single: lang_single,
+                               with_edition: with_edition),
+          "/",
+          typed_stage.abbreviation,
+          " ",
+          number.value,
+          (date ? ":#{date.year}" : ""),
+        ].join
+      end
+    end
+  end
+end

data/lib/pubid/idf/urn_generator.rb

@@ -0,0 +1,84 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Idf
+    class UrnGenerator < Pubid::UrnGenerator::Base
+      def urn_type
+        return nil unless identifier.type
+
+        identifier.type.abbr.to_s.downcase
+      end
+
+      def urn_number
+        return nil unless identifier.number
+
+        identifier.number.value.to_s
+      end
+
+      def urn_part
+        return nil unless identifier.part
+
+        "-#{identifier.part.value}"
+      end
+
+      def urn_subpart
+        return nil unless identifier.subpart
+
+        "-#{identifier.subpart.value}"
+      end
+
+      def urn_year
+        if identifier.date&.year
+          return identifier.date.year.to_s
+        end
+
+        identifier.year&.to_s
+      end
+
+      def urn_edition
+        return nil unless identifier.edition
+
+        num = identifier.edition.number
+        return nil unless num
+
+        "ed.#{num}"
+      end
+
+      def generate
+        parts = ["urn", "idf"]
+        parts << urn_number if urn_number
+        parts << urn_part if urn_part
+        parts << urn_subpart if urn_subpart
+        parts << urn_year if urn_year
+        parts << urn_edition if urn_edition
+        parts << urn_type if urn_type
+
+        if identifier.publisher
+          parts[1] = identifier.publisher.body.to_s.downcase
+        end
+
+        if identifier.copublishers&.any?
+          copubs = identifier.copublishers.map(&:body)
+          parts[1] = "#{parts[1]}-#{copubs.join('-').downcase}"
+        end
+
+        if identifier.languages&.any?
+          parts << identifier.languages.map(&:code).join(",")
+        end
+
+        if identifier.is_a?(SupplementIdentifier)
+          if identifier.typed_stage
+            supp_type = identifier.typed_stage.type_code.to_s
+            parts << supp_type if supp_type
+          end
+
+          if identifier.number
+            parts << identifier.number.value.to_s
+          end
+        end
+
+        parts.join(":")
+      end
+    end
+  end
+end

data/lib/pubid/idf.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+module Pubid
+  module Idf
+    autoload :Builder, "#{__dir__}/idf/builder"
+    autoload :Identifier, "#{__dir__}/idf/identifier"
+    autoload :Identifiers, "#{__dir__}/idf/identifiers"
+    autoload :Parser, "#{__dir__}/idf/parser"
+    autoload :Scheme, "#{__dir__}/idf/scheme"
+    autoload :SingleIdentifier, "#{__dir__}/idf/single_identifier"
+    autoload :SupplementIdentifier, "#{__dir__}/idf/supplement_identifier"
+    autoload :UrnGenerator, "#{__dir__}/idf/urn_generator"
+
+    def self.parse(identifier)
+      parser = Parser.new
+      builder = Builder.new
+
+      parsed = parser.parse(identifier)
+      builder.build(parsed)
+    end
+  end
+end
+
+# Register Uidf flavor with the registry
+Pubid::Registry.register(:idf, Pubid::Idf)