relaton-doi 2.1.2 → 2.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2a94f21c895d9262dbe8ac4ff23fdf39d90222ae4870932f467f8b29cf71f905
-  data.tar.gz: d927cd65ed6552b679b85625433c8afc6a41d9d5adda9dec8f03cfa03647fe3e
+  metadata.gz: 1f985958ac631dbcb90d8d435d4cd8d771ef1eb661096bd62d0aa05ea0739291
+  data.tar.gz: f0e7a7392db7ff8e082682c92afa15eabdad7230d35cb96335068f5ddaebd14f
 SHA512:
-  metadata.gz: 9b9ab1daeaa246358597b904ebdd6b606b0fd31caef80d7de01b76d07c1eb75451637df51424279771b97e67577c28f2109a43bfc6beb2cb2a0007371e02630a
-  data.tar.gz: b65e7cfdd691f5278a92da2a8b010d8f0bba91b0653733d1fb07665f2527a2f5f2905f58b3450a0db47ea61ebd256b158ea8760431ef8051eadb677f6c662a53
+  metadata.gz: e1474c8687f0772f77aa5a29cd5394722c12700a041bdb70cfab7fd2f84cb36d16f4cee676de366d262a2344075197b2fd6b18ea615c373495fc83f94756591d
+  data.tar.gz: fd1d94c456aed217671bd968d60815f5e06ed5d87bad05efd950f04fe43e6e1a46cbb1c8f8c28f8a57f90520894c384de29a29da7fd1a051533342ea5eac6fb8

data/CLAUDE.md

@@ -43,3 +43,19 @@ Key classes in `lib/relaton/doi/`:
 - `TYPES` — maps 23 Crossref document types to Relaton types (e.g., `"book-chapter"` → `"inbook"`)
 - `REALATION_TYPES` — maps 37 Crossref relation types to Relaton relation types
 - `COUNTRIES` — `%w[USA]`, used by `parse_place` to distinguish country vs region
+
+## Crossref Markup Handling
+
+`Parser#normalize_markup` decodes the HTML entities of raw Crossref content. Crossref
+sometimes returns the JATS markup entity-encoded, and the relaton-bib sanitizer detects a
+tag by a real `<`, so it would treat the encoded form as plain text.
+
+`Bib::Title` and `Bib::Abstract` are `LocalizedMarkedUpString` subclasses, so their
+`content=` setter runs `Relaton::Bib::Sanitizer` on assignment. Since relaton-bib 2.1.9 that
+sanitizer also removes the `jats:` and `xlink:` namespace prefixes. Relaton never declares
+those prefixes, so leaving them in place made the output fail every namespace-aware parser
+downstream, including relaton-render (metanorma-pdfa#99). relaton-doi carried its own prefix
+stripping until 2.1.9 shipped that fix, which is why the gemspec pins `~> 2.1.9`.
+
+The sanitizer removes only the prefixes it could not resolve. A namespace that the content
+declares itself survives, such as the MathML `xmlns` inside a `<stem>`.

data/lib/relaton/doi/parser.rb

@@ -209,10 +209,29 @@ module Relaton
       # @return [Bib::Title] The title.
       #
       def create_title(title, type = "main")
-        cnt = str_cleanup CGI.unescapeHTML(title)
+        cnt = str_cleanup normalize_markup(title)
         Bib::Title.new type: type, content: cnt, script: "Latn"
       end
 
+      #
+      # Decode the HTML entities of raw Crossref content.
+      #
+      # Crossref sometimes returns the JATS markup as HTML entities. The
+      # relaton-bib sanitizer detects a tag by a real `<`, so it treats the
+      # encoded form as plain text and leaves it alone. Decode the entities
+      # here, and the sanitizer maps the markup to the basicdoc set.
+      #
+      # The sanitizer removes the `jats:` and `xlink:` namespace prefixes
+      # itself since relaton-bib 2.1.9, so this method no longer does.
+      #
+      # @param [String] str The raw Crossref content.
+      #
+      # @return [String] The content without HTML entities.
+      #
+      def normalize_markup(str)
+        CGI.unescapeHTML(str)
+      end
+
       #
       # Parse a docidentifier from the source hash.
       #
@@ -303,9 +322,10 @@ module Relaton
       def parse_abstract
         return [] unless @src["abstract"]
 
-        content = @src["abstract"]
         abstract = Bib::Abstract.new(
-          content: content, language: "en", script: "Latn",
+          content: normalize_markup(@src["abstract"]),
+          language: "en",
+          script: "Latn",
         )
         [abstract]
       end
@@ -448,8 +468,10 @@ module Relaton
       # @return [Bib::Organization] The organization.
       #
       def create_org(name, abbreviation = nil)
-        n = [Bib::TypedLocalizedString.new(content: name)]
-        a = abbreviation ? Bib::LocalizedString.new(content: abbreviation) : nil
+        n = [Bib::TypedLocalizedString.new(content: CGI.unescapeHTML(name))]
+        a = if abbreviation
+              Bib::LocalizedString.new(content: CGI.unescapeHTML(abbreviation))
+            end
         Bib::Organization.new name: n, abbreviation: a
       end
 
@@ -462,11 +484,7 @@ module Relaton
         return [] unless @src["standards-body"]
 
         name, acronym = @src["standards-body"].values_at("name", "acronym")
-        org = create_org(
-          CGI.unescapeHTML(name),
-          acronym && CGI.unescapeHTML(acronym),
-        )
-        [contributor(org, "authorizer")]
+        [contributor(create_org(name, acronym), "authorizer")]
       end
 
       #
@@ -728,7 +746,8 @@ module Relaton
 
         @src["container-title"].map do |ct|
           contrib = create_authors_editors false, "editor"
-          bib = Bib::ItemBase.new(title: [Bib::Title.new(content: ct)], contributor: contrib)
+          title = Bib::Title.new content: normalize_markup(ct)
+          bib = Bib::ItemBase.new(title: [title], contributor: contrib)
           Bib::Relation.new(type: "includedIn", bibitem: bib)
         end
       end
@@ -777,7 +796,7 @@ module Relaton
                   else []
                   end
         con_ttl.map do |ct|
-          title = Bib::Title.new content: ct
+          title = Bib::Title.new content: normalize_markup(ct)
           Bib::Series.new title: [title], abbreviation: abbrev
         end
       end

data/lib/relaton/doi/version.rb

@@ -2,6 +2,6 @@
 
 module Relaton
   module Doi
-    VERSION = "2.1.2"
+    VERSION = "2.1.4"
   end
 end

data/relaton-doi.gemspec

@@ -34,7 +34,7 @@ Gem::Specification.new do |spec|
   # Uncomment to register a new dependency of your gem
   # spec.add_dependency "example-gem", "~> 1.0"
 
-  spec.add_dependency "relaton-bib", "~> 2.1.3"
+  spec.add_dependency "relaton-bib", "~> 2.1.9"
   spec.add_dependency "relaton-bipm", "~> 2.1.0"
   spec.add_dependency "relaton-ieee", "~> 2.1.0"
   spec.add_dependency "relaton-ietf", "~> 2.1.0"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-doi
 version: !ruby/object:Gem::Version
-  version: 2.1.2
+  version: 2.1.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-21 00:00:00.000000000 Z
+date: 2026-09-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: relaton-bib
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.3
+        version: 2.1.9
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.1.3
+        version: 2.1.9
 - !ruby/object:Gem::Dependency
   name: relaton-bipm
   requirement: !ruby/object:Gem::Requirement