relaton-bib 2.1.2 → 2.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 103ee7e7e99ea81a307302c1dd476f812a7b1f9b1653213062e0bf80b9950987
-  data.tar.gz: 031625043b1a7b9d6a2d2d674b68f500ccfec8f836c7d9d645a8f4e751cd88e1
+  metadata.gz: ddc9644848b2d2d3215b088b0490e2769f541d3415806d6cee1a7d5f5f459ea3
+  data.tar.gz: 1ed5a54ad4dc216b17c0c29bbec68248e36e243f918f4edf753b3827cf163e3a
 SHA512:
-  metadata.gz: 34d61ff26b50b995ac955707449111866cd15f30c68beda845f0ae3fcb7fe04e1e7999b8c560b3f874dac83e0777cbc7b26723000c8cfd8b0c2e7f11b734e7cf
-  data.tar.gz: 838061a378904a0a338e9c87f569099b45656e33614265eb07a61afaa9e7e0b76f5278faeb4e414451fc31c11936867c3db01e61e52f65cd7cc490510e1967bc
+  metadata.gz: 67bf2aa865f1b688e72c02e8b5c724a3db3a038ce4db56b9a20ed343ee5e39546c71d1fcf0b5390b2031c018290cbf99f8529f94cfb8dd41f63b06267f5800af
+  data.tar.gz: 7176d810c8e1290fe038b6bfc390ddfd5e1676fe9cafcb799deeb2a279c2f54369c9aa0a578ae2344052a0fa42a8932cbd716144478e0af82b0ea2d3ba531b6b

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 = "2.1.2".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: 2.1.2
+  version: 2.1.3
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-07 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