PDF/UA. Update rules about tagged content

PDF/UA-1(7.1-1 - 7.1-2), PDF/UA-2(8.2.2-1, 8.5.1-1)
veraPDF · Dec 27, 2023 · bfefc3d · bfefc3d
1 parent 5e46b51
commit bfefc3d
Show file tree

Hide file tree

Showing 5 changed files with 19 additions and 19 deletions.
diff --git a/PDF_UA/PDFUA-1.xml b/PDF_UA/PDFUA-1.xml
@@ -67,31 +67,31 @@
         <rule object="SEMarkedContent" tags="artifact">
             <id specification="ISO_14289_1" clause="7.1" testNumber="1"/>
             <description>Content marked as Artifact should not present inside tagged content</description>
-            <test>tag != 'Artifact' || parentStructureTag == null</test>
+            <test>tag != 'Artifact' || isTaggedContent == false</test>
             <error>
-                <message>Content marked as Artifact is present inside tagged content (tag %1)</message>
+                <message>Content marked as Artifact is present inside tagged content (parent struct element %1)</message>
                 <arguments>
-                    <argument>parentStructureTag</argument>
+                    <argument>parentStructureElementObjectKey</argument>
                 </arguments>
             </error>
             <references/>
         </rule>
         <rule object="SEMarkedContent" tags="artifact">
             <id specification="ISO_14289_1" clause="7.1" testNumber="2"/>
             <description>Tagged content should not present inside content marked as Artifact</description>
-            <test>parentStructureTag == null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length == 0</test>
+            <test>isTaggedContent == false || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length == 0</test>
             <error>
-                <message>Tagged content (tag %1) is present inside content marked as Artifact</message>
+                <message>Tagged content (parent struct element %1) is present inside content marked as Artifact</message>
                 <arguments>
-                    <argument>parentStructureTag</argument>
+                    <argument>parentStructureElementObjectKey</argument>
                 </arguments>
             </error>
             <references/>
         </rule>
         <rule object="SESimpleContentItem" tags="artifact">
             <id specification="ISO_14289_1" clause="7.1" testNumber="3"/>
             <description>Content shall be marked as Artifact or tagged as real content</description>
-            <test>parentStructureTag != null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
+            <test>isTaggedContent == true || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
             <error>
                 <message>Content is neither marked as Artifact nor tagged as real content</message>
                 <arguments/>

diff --git a/PDF_UA/PDFUA-2-ISO32005.xml b/PDF_UA/PDFUA-2-ISO32005.xml
@@ -91,7 +91,7 @@
         <rule object="SESimpleContentItem">
             <id specification="ISO_14289_2" clause="8.2.2" testNumber="1"/>
             <description>Content that is not considered real shall be an artifact</description>
-            <test>parentStructureTag != null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
+            <test>isTaggedContent == true || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
             <error>
                 <message>Content is neither marked as Artifact nor tagged as real content</message>
                 <arguments/>
@@ -438,17 +438,17 @@
             <description>The ActualText entry shall not contain any PUA values</description>
             <test>containsPUA == false</test>
             <error>
-                <message>The ActualText entry contains a Private Unicoide Area value</message>
+                <message>The ActualText entry contains a Private Unicode Area value</message>
                 <arguments/>
             </error>
             <references/>
         </rule>
-        <rule object="CosActualText">
+        <rule object="CosAlt">
             <id specification="ISO_14289_2" clause="8.4.3" testNumber="3"/>
             <description>The Alt entry shall not contain any PUA values</description>
             <test>containsPUA == false</test>
             <error>
-                <message>The Alt entry contains a Private Unicoide Area value</message>
+                <message>The Alt entry contains a Private Unicode Area value</message>
                 <arguments/>
             </error>
             <references/>
@@ -668,7 +668,7 @@
         <rule object="SESimpleContentItem">
             <id specification="ISO_14289_2" clause="8.5.1" testNumber="1"/>
             <description>Real content that does not possess the semantics of text objects and does not have an alternate textual representation shall be enclosed within Figure or Formula structure elements as appropriate</description>
-            <test>itemType == 'text' || parentStructureTag == null || ActualText != null || isArtifact == true || isFigure == true || isFormula == true</test>
+            <test>itemType == 'text' || isTaggedContent == false || ActualText != null || isArtifact == true || isFigure == true || isFormula == true</test>
             <error>
                 <message>Real content that does not possess the semantics of text objects and does not have an alternate textual representation is not enclosed within Figure or Formula structure elements</message>
                 <arguments/>

diff --git a/PDF_UA/PDFUA-2.xml b/PDF_UA/PDFUA-2.xml
@@ -91,7 +91,7 @@
         <rule object="SESimpleContentItem">
             <id specification="ISO_14289_2" clause="8.2.2" testNumber="1"/>
             <description>Content that is not considered real shall be an artifact</description>
-            <test>parentStructureTag != null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
+            <test>isTaggedContent == true || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
             <error>
                 <message>Content is neither marked as Artifact nor tagged as real content</message>
                 <arguments/>
@@ -438,17 +438,17 @@
             <description>The ActualText entry shall not contain any PUA values</description>
             <test>containsPUA == false</test>
             <error>
-                <message>The ActualText entry contains a Private Unicoide Area value</message>
+                <message>The ActualText entry contains a Private Unicode Area value</message>
                 <arguments/>
             </error>
             <references/>
         </rule>
-        <rule object="CosActualText">
+        <rule object="CosAlt">
             <id specification="ISO_14289_2" clause="8.4.3" testNumber="3"/>
             <description>The Alt entry shall not contain any PUA values</description>
             <test>containsPUA == false</test>
             <error>
-                <message>The Alt entry contains a Private Unicoide Area value</message>
+                <message>The Alt entry contains a Private Unicode Area value</message>
                 <arguments/>
             </error>
             <references/>
@@ -668,7 +668,7 @@
         <rule object="SESimpleContentItem">
             <id specification="ISO_14289_2" clause="8.5.1" testNumber="1"/>
             <description>Real content that does not possess the semantics of text objects and does not have an alternate textual representation shall be enclosed within Figure or Formula structure elements as appropriate</description>
-            <test>itemType == 'text' || parentStructureTag == null || ActualText != null || isArtifact == true || isFigure == true || isFormula == true</test>
+            <test>itemType == 'text' || isTaggedContent == false || ActualText != null || isArtifact == true || isFigure == true || isFormula == true</test>
             <error>
                 <message>Real content that does not possess the semantics of text objects and does not have an alternate textual representation is not enclosed within Figure or Formula structure elements</message>
                 <arguments/>

diff --git a/PDF_UA/WCAG-2-2-Complete.xml b/PDF_UA/WCAG-2-2-Complete.xml
@@ -33,7 +33,7 @@
         <rule object="SESimpleContentItem" tags="critical,machine,artifact">
             <id specification="ISO_14289_1" clause="7.1" testNumber="3"/>
             <description>Content shall be marked as Artifact or tagged as real content</description>
-            <test>parentStructureTag != null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
+            <test>isTaggedContent == true || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
             <error>
                 <message>Content is neither marked as Artifact nor tagged as real content</message>
                 <arguments/>

diff --git a/PDF_UA/WCAG-2-2-Machine.xml b/PDF_UA/WCAG-2-2-Machine.xml
@@ -33,7 +33,7 @@
         <rule object="SESimpleContentItem" tags="critical,machine,artifact">
             <id specification="ISO_14289_1" clause="7.1" testNumber="3"/>
             <description>Content shall be marked as Artifact or tagged as real content</description>
-            <test>parentStructureTag != null || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
+            <test>isTaggedContent == true || parentsTags.split('&amp;').filter(elem =&gt; elem == 'Artifact').length &gt; 0</test>
             <error>
                 <message>Content is neither marked as Artifact nor tagged as real content</message>
                 <arguments/>