fix: Render unicode characters in SVG elements correctly (#832)

* fix: Render unicode characters in SVG elements correctly * fix: Stop the warning when SVG element ends with an unicode character
ietf-tools · Jul 19, 2022 · ad44bb8 · ad44bb8
1 parent 63de72a
commit ad44bb8
Show file tree

Hide file tree

Showing 12 changed files with 179 additions and 117 deletions.
diff --git a/test.py b/test.py
@@ -505,7 +505,7 @@ def norm(t):
         #
         text = norm('\n'.join( p.text for p in self.pdfxml.xpath('.//Page/text') ))
         for e in self.root.xpath('./middle//*'):
-            if e.text and e.text.strip() and e.tag not in xml2rfc.util.unicode.unicode_content_tags:
+            if e.text and e.text.strip() and e.tag not in xml2rfc.util.unicode.unicode_content_tags and not xml2rfc.util.unicode.is_svg(e):
                 t =  norm(e.text.split(None, 1)[0])
                 self.assertIn(t, text)
 

diff --git a/tests/input/elements.xml b/tests/input/elements.xml
@@ -388,6 +388,20 @@ Unordered list, third bullet, fourth element:
                   <xi:include href="./ietf.svg"/>
                </artwork>
             </li>
+            <li>
+              <t>Unicode SVG rendering test</t>
+              <artwork alt="Unicode SVG" type="svg" align="center">
+                  <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 72 64">
+                      <path d="M 8,16 L 8,48" fill="none" stroke="black"/>
+                      <path d="M 64,16 L 64,48" fill="none" stroke="black"/>
+                      <path d="M 8,16 L 64,16" fill="none" stroke="black"/>
+                      <path d="M 8,48 L 64,48" fill="none" stroke="black"/>
+                      <g class="text">
+                          <text y="36" x="13">⊕⊖⊗⊘</text>
+                      </g>
+                  </svg>
+               </artwork>
+            </li>
          </ul>
       </section>
       <section>

diff --git a/tests/valid/elements.bom.text b/tests/valid/elements.bom.text
@@ -71,7 +71,7 @@ Table of Contents
    3.  Unordered list with sub-elements  . . . . . . . . . . . . . .   5
    4.  Ordered list with sub-elements  . . . . . . . . . . . . . . .   7
    5.  Definition list with sub-elements . . . . . . . . . . . . . .   9
-   6.  Table . . . . . . . . . . . . . . . . . . . . . . . . . . . .  10
+   6.  Table . . . . . . . . . . . . . . . . . . . . . . . . . . . .  11
    7.  Unicode Literals  . . . . . . . . . . . . . . . . . . . . . .  13
      7.1.  Single Characters . . . . . . . . . . . . . . . . . . . .  13
      7.2.  Character Strings . . . . . . . . . . . . . . . . . . . .  15
@@ -358,6 +358,11 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       (Artwork only available as svg: No external link available, see
       elements-00.html for artwork.)
 
+   *  Unicode SVG rendering test
+
+       (Artwork only available as svg: No external link available, see
+       elements-00.html for artwork.)
+
 4.  Ordered list with sub-elements
 
    1.    Ordered list, first bullet.  Indent="6".
@@ -377,15 +382,10 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
        voluptate vivere.  Sic faciam igitur, inquit: unam rem explicabo,
        eamque maximam, de physicis alias, et quidem locis pluribus.
 
-              Ordered list, third bullet, second element:
-              +-------------------------------------------+
-              |                                           |
-              |                  Artwork                  |
-              |                                           |
-              +-------------------------------------------+
 
-       Ordered list, third bullet, third element: Definition list,
-       element dt.
+
+
+
 
 
 
@@ -394,6 +394,15 @@ Author, et al.           Expires 13 January 2019                [Page 7]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+              Ordered list, third bullet, second element:
+              +-------------------------------------------+
+              |                                           |
+              |                  Artwork                  |
+              |                                           |
+              +-------------------------------------------+
+
+       Ordered list, third bullet, third element: Definition list,
+       element dt.
           Element dd.  Nisi mihi Phaedrum, inquam, tu mentitum aut
           Zenonem misisti.
 
@@ -433,15 +442,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
           Case Ambiguity [RFC8174], Appendix A.1 / Key Words Case
           Ambiguity [RFC8174] (Appendix A.1).
 
-       4.1  Sublist with '%p' parent counter element in the list
-            counter, item one
-
-       4.2  Item two.
-
-       4.3  Item three.
-
-
-
 
 
 
@@ -450,6 +450,13 @@ Author, et al.           Expires 13 January 2019                [Page 8]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+       4.1  Sublist with '%p' parent counter element in the list
+            counter, item one
+
+       4.2  Item two.
+
+       4.3  Item three.
+
 5.  Definition list with sub-elements
 
    Term 1  Definition list, first bullet.
@@ -491,13 +498,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       1.  Definition list, third bullet, fifth element: Ordered list,
           element li.  Text only.
 
-      2.  Definition list, third bullet, fifth element: Ordered list,
-          element t.  Nam cum ad me de virtute misisti.  Quae est enim
-          contra Cyrenaicos satis acute, nihil ad iucunde vivendum
-          reperiri posse, quod coniunctione tali sit aptius.  Quae etsi
-          mihi nullo modo nec divelli nec distrahi possint, sic de
-          iustitia iudicandum est, quae non modo non impediri rationem
-          amicitiae, si summum bonum diceret, primum in eo essent.
 
 
 
@@ -506,6 +506,14 @@ Author, et al.           Expires 13 January 2019                [Page 9]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+      2.  Definition list, third bullet, fifth element: Ordered list,
+          element t.  Nam cum ad me de virtute misisti.  Quae est enim
+          contra Cyrenaicos satis acute, nihil ad iucunde vivendum
+          reperiri posse, quod coniunctione tali sit aptius.  Quae etsi
+          mihi nullo modo nec divelli nec distrahi possint, sic de
+          iustitia iudicandum est, quae non modo non impediri rationem
+          amicitiae, si summum bonum diceret, primum in eo essent.
+
           *  UL within OL within DL, item one
 
           *  UL within OL within DL, item two
@@ -545,14 +553,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       voluptate vivere.  Sic faciam igitur, inquit: unam rem explicabo,
       eamque maximam, de physicis alias, et quidem locis pluribus.
 
-6.  Table
-
-
-
-
-
-
-
 
 
 
@@ -562,6 +562,8 @@ Author, et al.           Expires 13 January 2019               [Page 10]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+6.  Table
+
          +-----+-----+-----------+
          |     |     |           |
          +-----+-----+-----+-----+
@@ -611,8 +613,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
 
-
-
 Author, et al.           Expires 13 January 2019               [Page 11]
 
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018

diff --git a/tests/valid/elements.pages.text b/tests/valid/elements.pages.text
@@ -71,7 +71,7 @@ Table of Contents
    3.  Unordered list with sub-elements  . . . . . . . . . . . . . .   5
    4.  Ordered list with sub-elements  . . . . . . . . . . . . . . .   7
    5.  Definition list with sub-elements . . . . . . . . . . . . . .   9
-   6.  Table . . . . . . . . . . . . . . . . . . . . . . . . . . . .  10
+   6.  Table . . . . . . . . . . . . . . . . . . . . . . . . . . . .  11
    7.  Unicode Literals  . . . . . . . . . . . . . . . . . . . . . .  13
      7.1.  Single Characters . . . . . . . . . . . . . . . . . . . .  13
      7.2.  Character Strings . . . . . . . . . . . . . . . . . . . .  15
@@ -358,6 +358,11 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       (Artwork only available as svg: No external link available, see
       elements-00.html for artwork.)
 
+   *  Unicode SVG rendering test
+
+       (Artwork only available as svg: No external link available, see
+       elements-00.html for artwork.)
+
 4.  Ordered list with sub-elements
 
    1.    Ordered list, first bullet.  Indent="6".
@@ -377,15 +382,10 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
        voluptate vivere.  Sic faciam igitur, inquit: unam rem explicabo,
        eamque maximam, de physicis alias, et quidem locis pluribus.
 
-              Ordered list, third bullet, second element:
-              +-------------------------------------------+
-              |                                           |
-              |                  Artwork                  |
-              |                                           |
-              +-------------------------------------------+
 
-       Ordered list, third bullet, third element: Definition list,
-       element dt.
+
+
+
 
 
 
@@ -394,6 +394,15 @@ Author, et al.          Expires January 13, 2019                [Page 7]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+              Ordered list, third bullet, second element:
+              +-------------------------------------------+
+              |                                           |
+              |                  Artwork                  |
+              |                                           |
+              +-------------------------------------------+
+
+       Ordered list, third bullet, third element: Definition list,
+       element dt.
           Element dd.  Nisi mihi Phaedrum, inquam, tu mentitum aut
           Zenonem misisti.
 
@@ -433,15 +442,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
           Case Ambiguity [RFC8174], Appendix A.1 / Key Words Case
           Ambiguity [RFC8174] (Appendix A.1).
 
-       4.1  Sublist with '%p' parent counter element in the list
-            counter, item one
-
-       4.2  Item two.
-
-       4.3  Item three.
-
-
-
 
 
 
@@ -450,6 +450,13 @@ Author, et al.          Expires January 13, 2019                [Page 8]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+       4.1  Sublist with '%p' parent counter element in the list
+            counter, item one
+
+       4.2  Item two.
+
+       4.3  Item three.
+
 5.  Definition list with sub-elements
 
    Term 1  Definition list, first bullet.
@@ -491,13 +498,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       1.  Definition list, third bullet, fifth element: Ordered list,
           element li.  Text only.
 
-      2.  Definition list, third bullet, fifth element: Ordered list,
-          element t.  Nam cum ad me de virtute misisti.  Quae est enim
-          contra Cyrenaicos satis acute, nihil ad iucunde vivendum
-          reperiri posse, quod coniunctione tali sit aptius.  Quae etsi
-          mihi nullo modo nec divelli nec distrahi possint, sic de
-          iustitia iudicandum est, quae non modo non impediri rationem
-          amicitiae, si summum bonum diceret, primum in eo essent.
 
 
 
@@ -506,6 +506,14 @@ Author, et al.          Expires January 13, 2019                [Page 9]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+      2.  Definition list, third bullet, fifth element: Ordered list,
+          element t.  Nam cum ad me de virtute misisti.  Quae est enim
+          contra Cyrenaicos satis acute, nihil ad iucunde vivendum
+          reperiri posse, quod coniunctione tali sit aptius.  Quae etsi
+          mihi nullo modo nec divelli nec distrahi possint, sic de
+          iustitia iudicandum est, quae non modo non impediri rationem
+          amicitiae, si summum bonum diceret, primum in eo essent.
+
           *  UL within OL within DL, item one
 
           *  UL within OL within DL, item two
@@ -545,14 +553,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
       voluptate vivere.  Sic faciam igitur, inquit: unam rem explicabo,
       eamque maximam, de physicis alias, et quidem locis pluribus.
 
-6.  Table
-
-
-
-
-
-
-
 
 
 
@@ -562,6 +562,8 @@ Author, et al.          Expires January 13, 2019               [Page 10]
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
+6.  Table
+
          +-----+-----+-----------+
          |     |     |           |
          +-----+-----+-----+-----+
@@ -611,8 +613,6 @@ Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018
 
 
 
-
-
 Author, et al.          Expires January 13, 2019               [Page 11]
 
 Internet-Draft       Xml2rfc Vocabulary V3 Elements            July 2018

diff --git a/tests/valid/elements.prepped.xml b/tests/valid/elements.prepped.xml
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<rfc xmlns:xi="http://www.w3.org/2001/XInclude" version="3" category="info" docName="elements-00" indexInclude="false" ipr="trust200902" obsoletes="1234,5678,9012,3456,7890" prepTime="2022-05-09T06:41:10" scripts="Cherokee,Common,Greek,Han,Hebrew,Latin" sortRefs="true" submissionType="independent" symRefs="true" tocDepth="3" tocInclude="true">
+<rfc xmlns:xi="http://www.w3.org/2001/XInclude" version="3" category="info" docName="elements-00" indexInclude="false" ipr="trust200902" obsoletes="1234,5678,9012,3456,7890" prepTime="2022-07-12T11:20:45" scripts="Cherokee,Common,Greek,Han,Hebrew,Latin" sortRefs="true" submissionType="independent" symRefs="true" tocDepth="3" tocInclude="true">
 
 
 
@@ -544,6 +544,20 @@ Unordered list, third bullet, fourth element:
             </svg>
           </artwork>
         </li>
+        <li pn="section-3-1.5">
+          <t indent="0" pn="section-3-1.5.1">Unicode SVG rendering test</t>
+          <artwork alt="Unicode SVG" type="svg" align="center" pn="section-3-1.5.2">
+                  <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 72 64">
+              <path d="M 8,16 L 8,48" fill="none" stroke="black"/>
+              <path d="M 64,16 L 64,48" fill="none" stroke="black"/>
+              <path d="M 8,16 L 64,16" fill="none" stroke="black"/>
+              <path d="M 8,48 L 64,48" fill="none" stroke="black"/>
+              <g class="text">
+                <text y="36" x="13">⊕⊖⊗⊘</text>
+              </g>
+            </svg>
+          </artwork>
+        </li>
       </ul>
     </section>
     <section numbered="true" removeInRFC="false" toc="include" pn="section-4">

diff --git a/tests/valid/elements.text b/tests/valid/elements.text
@@ -305,6 +305,11 @@ Table of Contents
       (Artwork only available as svg: No external link available, see
       elements-00.html for artwork.)
 
+   *  Unicode SVG rendering test
+
+       (Artwork only available as svg: No external link available, see
+       elements-00.html for artwork.)
+
 4.  Ordered list with sub-elements
 
    1.    Ordered list, first bullet.  Indent="6".

diff --git a/tests/valid/elements.v3.html b/tests/valid/elements.v3.html
@@ -15,7 +15,7 @@
 <meta content="
        This is the abstract. 
     " name="description">
-<meta content="xml2rfc 3.12.7" name="generator">
+<meta content="xml2rfc 3.13.0" name="generator">
 <meta content="elements-00" name="ietf.draft">
 <link href="tests/input/elements.xml" rel="alternate" type="application/rfc+xml">
 <link href="#copyright" rel="license">
@@ -552,6 +552,20 @@ <h2 id="name-unordered-list-with-sub-ele">
               <path d="M3,26h5v5h-5zM168,26h5v5h-5z"></path>
             </svg><a href="#section-3-1.4.2" class="pilcrow">¶</a>
 </div>
+</li>
+        <li class="normal" id="section-3-1.5">
+          <p id="section-3-1.5.1">Unicode SVG rendering test<a href="#section-3-1.5.1" class="pilcrow">¶</a></p>
+<div class="alignCenter art-svg artwork" id="section-3-1.5.2">
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 72 64">
+              <path d="M 8,16 L 8,48" fill="none" stroke="black"></path>
+              <path d="M 64,16 L 64,48" fill="none" stroke="black"></path>
+              <path d="M 8,16 L 64,16" fill="none" stroke="black"></path>
+              <path d="M 8,48 L 64,48" fill="none" stroke="black"></path>
+              <g class="text">
+                <text y="36" x="13">⊕⊖⊗⊘</text>
+              </g>
+            </svg><a href="#section-3-1.5.2" class="pilcrow">¶</a>
+</div>
 </li>
       </ul>
 </section>