New test suite dependencies to better handle HTML versions (support a…

…nd default) for serialized output; + new tests for serialization edge cases
w3c · Nov 29, 2019 · 82a0f7a · 82a0f7a
1 parent b21c1d3
commit 82a0f7a
Show file tree

Hide file tree

Showing 11 changed files with 391 additions and 8 deletions.
diff --git a/admin/catalog-schema.xsd b/admin/catalog-schema.xsd
@@ -881,6 +881,8 @@
                                 <xs:enumeration value="disabling_output_escaping"/>
                                 <xs:enumeration value="dynamic_evaluation"/>
                                 <xs:enumeration value="higher_order_functions"/>
+                                <xs:enumeration value="HTML4"/>
+                                <xs:enumeration value="HTML5"/>
                                 <xs:enumeration value="namespace_axis"/>
                                 <xs:enumeration value="schema_aware"/>
                                 <xs:enumeration value="built_in_derived_types"/>
@@ -1281,6 +1283,28 @@
         </xs:complexType>
     </xs:element>
 
+    <xs:element name="default_html_version" substitutionGroup="dependency">
+        <xs:annotation>
+            <xs:documentation>
+                <p>Identifies the default HTML version for serialized output.</p>
+            </xs:documentation>
+        </xs:annotation>
+        <xs:complexType>
+            <xs:complexContent>
+                <xs:restriction base="dependencyType">
+                    <xs:attribute name="value">
+                        <xs:simpleType>
+                            <xs:restriction base="xs:string">
+                                <xs:enumeration value="4"/>
+                                <xs:enumeration value="5"/>
+                            </xs:restriction>
+                        </xs:simpleType>
+                    </xs:attribute>
+                </xs:restriction>
+            </xs:complexContent>
+        </xs:complexType>
+    </xs:element>
+
     <xs:element name="detect_accumulator_cycles" substitutionGroup="dependency" type="dependencyTypeTrue">
         <xs:annotation>
             <xs:documentation>

diff --git a/tests/decl/character-map/_character-map-test-set.xml b/tests/decl/character-map/_character-map-test-set.xml
@@ -511,6 +511,7 @@
       <description>Test that characters produced by a character map are immune to Unicode normalization</description>
       <keywords>single-character-map xml-output-method</keywords>
       <created by="Michael Kay" on="2016-02-18"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Use numeric character references in regex"/>
       <environment ref="charmap001"/>
       <dependencies>
          <spec value="XSLT20+"/>
@@ -520,11 +521,11 @@
          <output serialize="yes"/>
       </test>
       <result>
-         <all-of>
+         <any-of>
             <!-- The first c-cedilla is in composed form as codepoint (231); the second is in decomposed form as (99, 807) -->
-            <!-- The "." in the regex matches codepoint 807, but I'm having difficulty expressing this -->
-            <serialization-matches>&lt;out>ab#&#231;#&#99;.de&lt;/out></serialization-matches>
-         </all-of>
+            <serialization-matches>&lt;out>ab#&#231;#&#99;&#807;de&lt;/out></serialization-matches>
+            <serialization-matches>&lt;out>ab#&#231;#&#99;&#x327;de&lt;/out></serialization-matches>
+         </any-of>
       </result>
    </test-case>
 
@@ -563,4 +564,21 @@
          <error code="XTSE0010"/>
       </result>
    </test-case>
+
+   <test-case name="character-map-028">
+      <description>Test that characters produced by a character map are immune to Unicode normalization</description>
+      <keywords>single-character-map xml-output-method</keywords>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="charmap001"/>
+      <dependencies>
+         <spec value="XSLT20+"/>
+      </dependencies>
+      <test>
+         <stylesheet file="character-map-028.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <serialization-matches>&lt;out att=['"]ab#&#231;#&#99;&#807;de['"]>ab#&#231;#&#99;&#807;de&lt;/out></serialization-matches>
+      </result>
+   </test-case>
 </test-set>
diff --git a/tests/decl/character-map/character-map-028.xsl b/tests/decl/character-map/character-map-028.xsl
@@ -0,0 +1,16 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="2.0">
+
+  <!-- test that characters produced by a character map are immune to Unicode normalization -->
+
+  <xsl:character-map name="map01">
+    <xsl:output-character character="c" string="#ç#"/>
+  </xsl:character-map>
+
+  <xsl:output method="xml" use-character-maps="map01" normalization-form="NFD"/>
+
+  <xsl:template match="/">
+    <out att="abcçde">abcçde</out>
+  </xsl:template>
+
+</xsl:stylesheet>
diff --git a/tests/decl/output/_output-test-set.xml b/tests/decl/output/_output-test-set.xml
@@ -198,6 +198,7 @@
          @escape-uri-attributes=yes.</description>
       <created by="Michael Kay" on="2012-10-30"/>
       <modified by="John Lumley" on="2014-09-02" change="Declared serialization requirement"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Add variant with decimal numeric character references"/>
       <environment ref="output-0102"/>
       <dependencies>
          <spec value="XSLT20+"/>
@@ -207,7 +208,10 @@
          <output serialize="yes"/>
       </test>
       <result>
-         <serialization-matches><![CDATA[accesskey="&#x96;"]]></serialization-matches>
+         <any-of>
+            <serialization-matches><![CDATA[accesskey="&#x96;"]]></serialization-matches>
+            <serialization-matches><![CDATA[accesskey="&#150;"]]></serialization-matches>
+         </any-of>
       </result>
    </test-case>
 
@@ -256,6 +260,7 @@
          @escape-uri-attributes=no.</description>
       <created by="Michael Kay" on="2012-10-30"/>
       <modified by="John Lumley" on="2014-09-02" change="Declared serialization requirement"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Add variant with decimal numeric character references"/>
       <environment ref="output-0103"/>
       <dependencies>
          <spec value="XSLT20+"/>
@@ -265,7 +270,10 @@
          <output serialize="yes"/>
       </test>
       <result>
-         <serialization-matches><![CDATA[href="&#x96;"]]></serialization-matches>
+         <any-of>
+            <serialization-matches><![CDATA[href="&#x96;"]]></serialization-matches>
+            <serialization-matches><![CDATA[href="&#150;"]]></serialization-matches>
+         </any-of>
       </result>
    </test-case>
 
@@ -276,6 +284,7 @@
       <modified by="Tim Mills" on="2013-01-29"
          change="added variant with hex encoding of character references"/>
       <modified by="John Lumley" on="2014-09-02" change="Declared serialization requirement"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Add variant with decimal numeric character references"/>
       <environment ref="output-0103"/>
       <dependencies>
          <spec value="XSLT20+"/>
@@ -288,6 +297,7 @@
          <any-of>
             <serialization-matches><![CDATA[href="% %C2%96 &#x96; a &#34;  ¡ &lt; &gt; &amp; end"]]></serialization-matches>
             <serialization-matches><![CDATA[href="% %C2%96 &#x96; a &#x22;  ¡ &lt; &gt; &amp; end"]]></serialization-matches>
+            <serialization-matches><![CDATA[href="% %C2%96 &#150; a &#34;  ¡ &lt; &gt; &amp; end"]]></serialization-matches>
          </any-of>
       </result>
    </test-case>
@@ -315,6 +325,7 @@
          @escape-uri-attributes=no.</description>
       <created by="Michael Kay" on="2012-10-30"/>
       <modified by="John Lumley" on="2014-09-02" change="Declared serialization requirement"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Add variant with decimal numeric character references"/>
       <environment ref="output-0103"/>
       <dependencies>
          <spec value="XSLT20+"/>
@@ -324,7 +335,10 @@
          <output serialize="yes"/>
       </test>
       <result>
-         <serialization-matches><![CDATA[accesskey="&#x96;"]]></serialization-matches>
+         <any-of>
+            <serialization-matches><![CDATA[accesskey="&#x96;"]]></serialization-matches>
+            <serialization-matches><![CDATA[accesskey="&#150;"]]></serialization-matches>
+         </any-of>
       </result>
    </test-case>
 
@@ -680,6 +694,113 @@
          </all-of>
       </result>
    </test-case>
+
+   <test-case name="output-0115b">
+      <description>Test XHTML output with cdata-section-elements that have (non-ASCII) characters
+         not representable in the character encoding being used for output (US-ASCII)</description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT20+"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0115b.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <all-of>
+            <serialization-matches><![CDATA[<\?xml]]></serialization-matches>
+            <serialization-matches><![CDATA[<html xmlns="http://www.w3.org/1999/xhtml"><out><example>]]></serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[foo \]\]&gt;</serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[ bar\]\]&gt;</serialization-matches>
+            <any-of>
+               <serialization-matches><![CDATA[>&#xaa;<]]></serialization-matches>
+               <serialization-matches><![CDATA[>&#170;<]]></serialization-matches>
+            </any-of>
+         </all-of>
+      </result>
+   </test-case>
+
+   <test-case name="output-0115c">
+      <description>Test XHTML output with cdata-section-elements that have (non-ASCII) characters
+         not representable in the character encoding being used for output (US-ASCII);
+         not affected by character maps</description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT20+"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0115c.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <all-of>
+            <serialization-matches><![CDATA[<\?xml]]></serialization-matches>
+            <serialization-matches><![CDATA[<html xmlns="http://www.w3.org/1999/xhtml"><out><example>]]></serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[foo \]\]&gt;</serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[ bar\]\]&gt;</serialization-matches>
+            <any-of>
+               <serialization-matches><![CDATA[>&#xaa;<]]></serialization-matches>
+               <serialization-matches><![CDATA[>&#170;<]]></serialization-matches>
+            </any-of>
+         </all-of>
+      </result>
+   </test-case>
+
+   <test-case name="output-0115d">
+      <description>Test XHTML output with cdata-section-elements that have (non-ASCII) characters
+         not representable in the character encoding being used for output (US-ASCII);
+         but unicode normalized (NFD) </description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT20+"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0115d.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <all-of>
+            <serialization-matches><![CDATA[<\?xml]]></serialization-matches>
+            <serialization-matches><![CDATA[<html xmlns="http://www.w3.org/1999/xhtml"><out><example>]]></serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[foo c\]\]&gt;</serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[ bar\]\]&gt;</serialization-matches>
+            <any-of>
+               <serialization-matches><![CDATA[>&#807;<]]></serialization-matches>
+               <serialization-matches><![CDATA[>&#x327;<]]></serialization-matches>
+            </any-of>
+         </all-of>
+      </result>
+   </test-case>
+
+   <test-case name="output-0115e">
+      <description>Test XHTML output with cdata-section-elements that have (non-ASCII) characters
+         not representable in the character encoding being used for output (US-ASCII);
+         but unicode normalized (NFC) </description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT20+"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0115e.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <all-of>
+            <serialization-matches><![CDATA[<\?xml]]></serialization-matches>
+            <serialization-matches><![CDATA[<html xmlns="http://www.w3.org/1999/xhtml"><out><example>]]></serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[foo \]\]&gt;</serialization-matches>
+            <serialization-matches>&lt;!\[CDATA\[ bar\]\]&gt;</serialization-matches>
+            <any-of>
+               <serialization-matches><![CDATA[>&#xe7;<]]></serialization-matches>
+               <serialization-matches><![CDATA[>&#231;<]]></serialization-matches>
+            </any-of>
+         </all-of>
+      </result>
+   </test-case>
 
    <test-case name="output-0116">
       <description>Test empty elements with empty content model in XHTML output and
@@ -2672,9 +2793,12 @@
       <created by="Michael Kay" on="2012-10-30"/>
       <modified by="Tim Mills" on="2013-01-29" change="error to assert-serialization-error"/>
       <modified by="John Lumley" on="2014-09-02" change="Declared serialization requirement"/>
+      <modified by="Debbie Lockett" on="2019-11-29" change="Declared requirement for HTML serialization version less than 5.0"/>
       <environment ref="output-01"/>
       <dependencies>
          <spec value="XSLT20+"/>
+         <feature value="HTML4"/>
+         <default_html_version value="4"/>
       </dependencies>
       <test>
          <stylesheet file="output-0195.xsl"/>
@@ -2684,6 +2808,49 @@
          <assert-serialization-error code="SERE0014"/>
       </result>
    </test-case>
+
+   <test-case name="output-0195a">
+      <description>Test that no error is raised if the output method is HTML, with default version 5.0, and the result tree
+         contains characters in the #x7F-#x9F range.</description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT30+"/>
+         <feature value="HTML5"/>
+         <default_html_version value="5"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0195.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <any-of>
+            <serialization-matches><![CDATA[<doc>&#x9f;</doc>]]></serialization-matches>
+            <serialization-matches><![CDATA[<doc>&#159;</doc>]]></serialization-matches>
+         </any-of>
+      </result>
+   </test-case>
+
+   <test-case name="output-0195b">
+      <description>Test that no error is raised if the output method is HTML, version 5.0, and the result tree
+         contains characters in the #x7F-#x9F range.</description>
+      <created by="Debbie Lockett" on="2019-11-29"/>
+      <environment ref="output-01"/>
+      <dependencies>
+         <spec value="XSLT30+"/>
+         <feature value="HTML5"/>
+      </dependencies>
+      <test>
+         <stylesheet file="output-0195b.xsl"/>
+         <output serialize="yes"/>
+      </test>
+      <result>
+         <any-of>
+            <serialization-matches><![CDATA[<doc>&#x9f;</doc>]]></serialization-matches>
+            <serialization-matches><![CDATA[<doc>&#159;</doc>]]></serialization-matches>
+         </any-of>
+      </result>
+   </test-case>
 
    <test-case name="output-0196">
       <description>Test that an error is raised if the output method is HTML and &gt; appears within

diff --git a/tests/decl/output/output-0115b.xsl b/tests/decl/output/output-0115b.xsl
@@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<t:transform xmlns="http://www.w3.org/1999/xhtml"
+             xmlns:t="http://www.w3.org/1999/XSL/Transform"
+             version="2.0">
+
+   <t:output method="xhtml"
+             cdata-section-elements="example"
+             indent="no"
+             encoding="US-ASCII"/>
+   <!-- Purpose: Test XHTML output with cdata-section-elements that have non-ASCII character -->
+
+   <t:template match="/">
+      <html>
+         <out>
+            <example>foo &#xaa; bar</example>
+         </out>
+      </html>
+   </t:template>
+</t:transform>
diff --git a/tests/decl/output/output-0115c.xsl b/tests/decl/output/output-0115c.xsl
@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<t:transform xmlns="http://www.w3.org/1999/xhtml"
+             xmlns:t="http://www.w3.org/1999/XSL/Transform"
+             version="2.0">
+
+   <t:output method="xhtml"
+             cdata-section-elements="example"
+             indent="no"
+             encoding="US-ASCII"
+             use-character-maps="format1" />
+   <!-- Purpose: Test XHTML output with cdata-section-elements that have non-ASCII character -->
+
+   <t:character-map name="format1">
+      <t:output-character character="&#170;" string="A"/>
+   </t:character-map>
+
+   <t:template match="/">
+      <html>
+         <out>
+            <example>foo &#xaa; bar</example>
+         </out>
+      </html>
+   </t:template>
+</t:transform>