relaton-bib 2.1.1 → 2.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dbd5aea414046c022dca2c76a39b03469e284b3e40e5f466d45cc2095b872426
-  data.tar.gz: 549058e3a8f7d02fa187cc49764c674894bbf8853ec1aca87de367320f8a3700
+  metadata.gz: ddc9644848b2d2d3215b088b0490e2769f541d3415806d6cee1a7d5f5f459ea3
+  data.tar.gz: 1ed5a54ad4dc216b17c0c29bbec68248e36e243f918f4edf753b3827cf163e3a
 SHA512:
-  metadata.gz: 247065b32df801e9e0d4b01b66ca3e9ce3c17840eb7209f61d0717df322e84ef0996b1de3d706990b774733f3018e5dc8fb0c4f36a320ca8f2b94b5732163748
-  data.tar.gz: 31e0342c3793206c94478852cec92e31f4274aca78f69ed64b7ad2e79a39b66b6e68e326e22e5b38e9f8ecd2c69e38e4942a2939b7175a3869b7d73dcc273a8a
+  metadata.gz: 67bf2aa865f1b688e72c02e8b5c724a3db3a038ce4db56b9a20ed343ee5e39546c71d1fcf0b5390b2031c018290cbf99f8529f94cfb8dd41f63b06267f5800af
+  data.tar.gz: 7176d810c8e1290fe038b6bfc390ddfd5e1676fe9cafcb799deeb2a279c2f54369c9aa0a578ae2344052a0fa42a8932cbd716144478e0af82b0ea2d3ba531b6b

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

@@ -12,11 +12,37 @@ module Relaton
         map_element "text", to: :text
       end
 
+      # Returns the explicit text if set, else the Isoics description for
+      # `code`. Kept for consumers that read `.text` directly.
       def text
-        val = @text
-        return val if val && !val.empty?
+        return @text if @text.is_a?(String) && !@text.empty?
 
-        Isoics.fetch(code)&.description if code
+        Isoics.fetch(code)&.description if code.is_a?(String) && !code.empty?
+      end
+
+      # When code is assigned, eagerly populate text from Isoics if no
+      # explicit text has been set. Going through the public writer
+      # registers the value with the lutaml-model `value_set_for` tracker
+      # so the attribute is emitted on serialization.
+      def code=(val)
+        super
+        return unless val.is_a?(String) && !val.empty?
+        return if @text.is_a?(String) && !@text.empty?
+
+        description = Isoics.fetch(val)&.description
+        self.text = description if description
+      end
+
+      # When the deserializer reaches the end of the XML element and
+      # records that <text> was absent, it calls `using_default_for(:text)`
+      # to mark the attribute as default-valued (suppressing serialization).
+      # Refuse that mark if we've already populated text from Isoics so the
+      # value survives round-trip. See #112.
+      def using_default_for(attribute_name)
+        return if attribute_name == :text &&
+          @text.is_a?(String) && !@text.empty?
+
+        super
       end
     end
   end

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

@@ -26,7 +26,14 @@ module Relaton
     end
 
     class LocalizedMarkedUpString < LocalizedStringAttrs
+      module ContentSanitization
+        def content=(value)
+          super(Relaton::Bib::Sanitizer.sanitize(value))
+        end
+      end
+
       attribute :content, :string, raw: true
+      prepend ContentSanitization
 
       xml do
         map_all to: :content

data/lib/relaton/bib/sanitizer.rb

@@ -0,0 +1,47 @@
+require "nokogiri"
+
+module Relaton
+  module Bib
+    # Strips inline markup not in the basicdoc PureTextElement set
+    # (plus <p>, <eref>, <xref>) from raw marked-up content strings.
+    # Disallowed elements are unwrapped: tags removed, inner text kept.
+    module Sanitizer
+      ALLOWED = %w[
+        em strong sub sup tt underline strike smallcap br stem
+        p eref xref
+      ].freeze
+
+      RENAME = {
+        "italic" => "em",
+      }.freeze
+
+      TAG_RX = %r{<[a-zA-Z/!?]}
+
+      def self.sanitize(content)
+        return content unless sanitizable?(content)
+
+        fragment = Nokogiri::XML::DocumentFragment.parse(content)
+        return content if fragment.errors.any?
+
+        sanitize_children(fragment)
+        fragment.children.map { |c| c.to_xml(encoding: "UTF-8") }.join
+      end
+
+      def self.sanitizable?(content)
+        content.is_a?(::String) && !content.empty? && content.match?(TAG_RX)
+      end
+      private_class_method :sanitizable?
+
+      def self.sanitize_children(node)
+        node.children.to_a.each do |child|
+          next unless child.element?
+
+          child.name = RENAME[child.name] if RENAME.key?(child.name)
+          sanitize_children(child)
+          child.replace(child.children) unless ALLOWED.include?(child.name)
+        end
+      end
+      private_class_method :sanitize_children
+    end
+  end
+end

data/lib/relaton/bib/version.rb

@@ -1,5 +1,5 @@
 module Relaton
   module Bib
-    VERSION = "2.1.1".freeze
+    VERSION = "2.1.3".freeze
   end
 end

data/lib/relaton/bib.rb

@@ -7,6 +7,7 @@ require "rfcxml"
 require "relaton/core"
 require_relative "bib/version"
 require_relative "bib/util"
+require_relative "bib/sanitizer"
 require_relative "bib/namespace_helper"
 require_relative "bib/item_data"
 require_relative "bib/model/item"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-bib
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.1.3
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-06 00:00:00.000000000 Z
+date: 2026-05-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bibtex-ruby
@@ -232,6 +232,7 @@ files:
 - lib/relaton/bib/model/validity.rb
 - lib/relaton/bib/model/version.rb
 - lib/relaton/bib/namespace_helper.rb
+- lib/relaton/bib/sanitizer.rb
 - lib/relaton/bib/util.rb
 - lib/relaton/bib/version.rb
 - relaton-bib.gemspec