Debug insertion of <u> for unicode characters, was passing through &l…

…t; as decoded <: #216
metanorma · Dec 5, 2024 · 5894ec4 · 5894ec4
1 parent 5e419d4
commit 5894ec4
Show file tree

Hide file tree

Showing 4 changed files with 46 additions and 17 deletions.
diff --git a/lib/isodoc/ietf/cleanup_inline.rb b/lib/isodoc/ietf/cleanup_inline.rb
@@ -3,11 +3,11 @@ module Ietf
     class RfcConvert < ::IsoDoc::Convert
       def u_cleanup(xmldoc)
         xmldoc.traverse do |n|
-          next unless n.text?
-          next unless %w(t blockquote li dd preamble td th annotation)
-            .include? n.parent.name
-
-          n.replace(n.text.gsub(/[\u0080-\uffff]/, "<u>\\0</u>"))
+          n.text? or next
+          %w(t blockquote li dd preamble td th annotation)
+            .include? n.parent.name or next
+          n.replace(@c.encode(n.text, :basic).gsub(/[\u0080-\uffff]/,
+                                                   "<u>\\0</u>"))
         end
       end
 

diff --git a/lib/metanorma/ietf/isodoc.rng b/lib/metanorma/ietf/isodoc.rng
@@ -17,7 +17,7 @@
   these elements; we just want one namespace for any child grammars
   of this.
 -->
-<!-- VERSION v1.4.0 -->
+<!-- VERSION v1.4.1 -->
 <grammar xmlns:a="http://relaxng.org/ns/compatibility/annotations/1.0" xmlns="http://relaxng.org/ns/structure/1.0" datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes">
   <include href="reqt.rng"/>
   <include href="basicdoc.rng">

diff --git a/spec/isodoc/cleanup_spec.rb b/spec/isodoc/cleanup_spec.rb
@@ -946,8 +946,8 @@
       <rfc xmlns:xi='http://www.w3.org/2001/XInclude' version='3'>
                <front>
                  <abstract>
-                 <author>Hello Χello</author>
-                 <t>Hello Χello</t>
+                 <author>Hello &lt;"Χello</author>
+                 <t>Hello &lt;"Χello</t>
                  </abstract>
                </front>
                <middle/>
@@ -959,17 +959,18 @@
       <front>
       <abstract>
       <author>
-        Hello &#x3A7;ello
+        Hello &lt;"&#x3A7;ello
       </author>
       <t>
         Hello
-        <u>&#x3A7;</u>
+        &lt;"<u>&#x3A7;</u>
         ello
       </t>
       </abstract> </front> <middle/> <back/> </rfc>
     OUTPUT
     expect(Xml::C14n.format(IsoDoc::Ietf::RfcConvert.new({})
-      .cleanup(Nokogiri::XML(input)).to_s)).to be_equivalent_to Xml::C14n.format(output)
+      .cleanup(Nokogiri::XML(input)).to_s))
+      .to be_equivalent_to Xml::C14n.format(output)
   end
 
   it "cleans up lists with single paragraphs" do

diff --git a/spec/isodoc/inline_spec.rb b/spec/isodoc/inline_spec.rb
@@ -1,6 +1,34 @@
 require "spec_helper"
 
 RSpec.describe IsoDoc::Ietf::RfcConvert do
+  it "respect &lt; &gt;" do
+    FileUtils.rm_f "test.rfc.xml"
+    input = <<~INPUT
+      #{BLANK_HDR}
+      <preface><foreword>
+      <p>&lt;pizza&gt;</p>
+      </foreword></preface>
+      <sections>
+      </iso-standard>
+    INPUT
+    IsoDoc::Ietf::RfcConvert.new({})
+      .convert("test", input, false)
+    expect(Xml::C14n.format(File.read("test.rfc.xml")))
+      .to be_equivalent_to Xml::C14n.format(<<~OUTPUT)
+       <rfc xmlns:xi="http://www.w3.org/2001/XInclude" category="std" ipr="trust200902" submissionType="IETF" xml:lang="en" version="3">
+          <front>
+             <title>Document title</title>
+             <seriesInfo value="" status="Published" stream="IETF" name="Internet-Draft" asciiName="Internet-Draft"/>
+             <abstract>
+                <t>&lt;pizza&gt;</t>
+             </abstract>
+          </front>
+          <middle/>
+          <back/>
+       </rfc>
+    OUTPUT
+  end
+
   it "processes inline formatting" do
     input = <<~INPUT
       <iso-standard xmlns="http://riboseinc.com/isoxml">
@@ -708,26 +736,26 @@
                          <em>word</em>
                          [term defined in
                          <xref target="ISO712" section="3.1, Figure a" relative="">
-     
-     
+
+
                </xref>
                          ]
                       </li>
                       <li>
                          <em>word</em>
                          [term defined in
                          <xref target="ISO712" section="3.1 and Figure b" relative="">
-     
-     
+
+
                </xref>
                          ]
                       </li>
                       <li>
                          <em>word</em>
                          [term defined in
                          <xref target="ISO712" section="3.1 and Figure b" relative="">
-     
-     
+
+
                The Aforementioned Citation
                </xref>
                          ]