relaton-bib 2.1.2 → 2.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 103ee7e7e99ea81a307302c1dd476f812a7b1f9b1653213062e0bf80b9950987
-  data.tar.gz: 031625043b1a7b9d6a2d2d674b68f500ccfec8f836c7d9d645a8f4e751cd88e1
+  metadata.gz: c5fed587d3ea43b2fdba3f26039e44b076eea06413c7d44c815c44054bc2006a
+  data.tar.gz: 1ce1ef4de4d2cc010e899971a247bba869ec67f588423dcd5e1e9d44beb36932
 SHA512:
-  metadata.gz: 34d61ff26b50b995ac955707449111866cd15f30c68beda845f0ae3fcb7fe04e1e7999b8c560b3f874dac83e0777cbc7b26723000c8cfd8b0c2e7f11b734e7cf
-  data.tar.gz: 838061a378904a0a338e9c87f569099b45656e33614265eb07a61afaa9e7e0b76f5278faeb4e414451fc31c11936867c3db01e61e52f65cd7cc490510e1967bc
+  metadata.gz: 10279cf57d50ddb7e0339815be6edbc74ebc8568ffae16e2ca75f802939d3027639615fe117f060dc5985d0e3b074d021a4aa8a2a73745c6dd8aac7f71928f6c
+  data.tar.gz: a53c8ca8225e43038fab4dc8c39dde6871e8fffdbe1bbc3816a47379dbf79f5033c4a8b5cb2eaefa5aba6529714f289507160c19e0fc70e54541ce18fbe53fae

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 +1,54 @@
+require "nokogiri"
+
+module Relaton
+  module Bib
+    # Strips inline markup not in the basicdoc PureTextElement set
+    # (plus <p>, <eref>, <xref>, <fn>) from raw marked-up content strings.
+    # Disallowed elements are unwrapped: tags removed, inner text kept.
+    #
+    # <fn> is admitted beyond strict PureTextElement because bibliographic
+    # titles in real Metanorma input routinely carry footnotes (e.g. ISO
+    # standards titles with a disclaimer footnote), and downstream
+    # consumers — notably relaton-render's own inline-tag allow-list —
+    # already accept <fn> as a legitimate child of <title>. Stripping it
+    # here would break the round-trip.
+    module Sanitizer
+      ALLOWED = %w[
+        em strong sub sup tt underline strike smallcap br stem
+        p eref xref fn
+      ].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 = "2.1.4".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"
@@ -32,7 +33,7 @@ module Relaton
     # @return [Hash{String=>String}] schema versions
     #
     def schema_versions
-      @@schema_versions ||= JSON.parse File.read(File.join(__dir__, "../../grammars/versions.json"))
+      @@schema_versions ||= JSON.parse File.read(File.join(__dir__, "bib/versions.json"))
     end
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-bib
 version: !ruby/object:Gem::Version
-  version: 2.1.2
+  version: 2.1.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-07 00:00:00.000000000 Z
+date: 2026-06-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bibtex-ruby
@@ -160,11 +160,6 @@ files:
 - bin/rspec
 - bin/setup
 - docs/hash.adoc
-- grammars/basicdoc.rng
-- grammars/biblio-compile.rng
-- grammars/biblio-standoc.rng
-- grammars/biblio.rng
-- grammars/versions.json
 - lib/relaton/bib.rb
 - lib/relaton/bib/converter/asciibib.rb
 - lib/relaton/bib/converter/asciibib/to_asciibib.rb
@@ -232,8 +227,10 @@ 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
+- lib/relaton/bib/versions.json
 - relaton-bib.gemspec
 homepage: https://github.com/relaton/relaton-bib
 licenses: