Is there a way to change the stylesheet so that it converts an XML document with empty tags as <tag / ">?

Question

I extracted some code from codeproject in order to re-document the XML document. Does anyone know how I can modify the stylesheet to make it so that the conversion of the XML file leads to empty tags appearing <tag />instead <tag></tag>?

// http://www.codeproject.com/Articles/43309/How-to-create-a-simple-XML-file-using-MSXML-in-C
MSXML2::IXMLDOMDocumentPtr FormatDOMDocument(MSXML2::IXMLDOMDocumentPtr pDoc)
{
    LPCSTR const static szStyleSheet =
        R"!(<?xml version="1.0" encoding="utf-8"?>)!"
        R"!(<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">)!"
        R"!(    <xsl:output method="xml" indent="yes"/>)!"
        R"!(    <xsl:template match="@* | node()">)!"
        R"!(        <xsl:copy>)!"
        R"!(            <xsl:apply-templates select="@* | node()"/>)!"
        R"!(        </xsl:copy>)!"
        R"!(    </xsl:template>)!"
        R"!(</xsl:stylesheet>)!";

    MSXML2::IXMLDOMDocumentPtr pXmlStyleSheet;
    pXmlStyleSheet.CreateInstance(__uuidof(MSXML2::DOMDocument60));
    pXmlStyleSheet->loadXML(szStyleSheet);

    MSXML2::IXMLDOMDocumentPtr pXmlFormattedDoc;
    pXmlFormattedDoc.CreateInstance(__uuidof(MSXML2::DOMDocument60));

    CComPtr<IDispatch> pDispatch;
    HRESULT hr = pXmlFormattedDoc->QueryInterface(IID_IDispatch, (void**)&pDispatch);
    if (SUCCEEDED(hr))
    {
        _variant_t    vtOutObject;
        vtOutObject.vt = VT_DISPATCH;
        vtOutObject.pdispVal = pDispatch;
        vtOutObject.pdispVal->AddRef();

        hr = pDoc->transformNodeToObject(pXmlStyleSheet, vtOutObject);
    }

    //By default it is writing the encoding = UTF-16. Let us change the encoding to UTF-8

    // <?xml version="1.0" encoding="UTF-8"?>
    MSXML2::IXMLDOMNodePtr pXMLFirstChild = pXmlFormattedDoc->GetfirstChild();
    // A map of the a attributes (vesrsion, encoding) values (1.0, UTF-8) pair
    MSXML2::IXMLDOMNamedNodeMapPtr pXMLAttributeMap =  pXMLFirstChild->Getattributes();
    MSXML2::IXMLDOMNodePtr pXMLEncodNode = pXMLAttributeMap->getNamedItem(_T("encoding"));
    pXMLEncodNode->PutnodeValue(_T("UTF-8"));    //encoding = UTF-8

    return pXmlFormattedDoc;
}

Answer 1

In this style sheet, where possible, empty tags are written (with MSXML6):

<?xml version="1.0" encoding="utf-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
    <xsl:output method="xml" indent="yes"/>

    <xsl:template match="@* | node()">
        <xsl:copy>
            <xsl:apply-templates select="@* | node()"/>
        </xsl:copy>
    </xsl:template>

    <xsl:template match="*[not(*) and not(normalize-space()) and not(comment()) and not(processing-instruction())]">
        <xsl:element name="{name()}" namespace="{namespace-uri()}">
            <xsl:copy-of select="./@*"/>
        </xsl:element>
    </xsl:template>
</xsl:stylesheet>

xsl:copy , , "" xsl:element. , xsl:copy-of.

, XML-:

<Document>
<empty> </empty>
<empty-2/>
<non-empty>
Some text
</non-empty>

<non-empty-2 some-attribute="attribute text">
<empty-3/>
<non-empty-3><empty-4/><empty-with-attribute another-attribute="some more text">    


</empty-with-attribute>
</non-empty-3>
</non-empty-2>

<abc:non-empty-with-namespace xmlns:abc="urn:test:abc">
<abc:empty-with-namespace abc:namespaced-attribute="namespaced attribute text"/>
</abc:non-empty-with-namespace>

<non-empty-comment>
<!-- A comment -->
</non-empty-comment>

<non-empty-proc-instr>
<?some-instruction?>
</non-empty-proc-instr>

</Document>

FormatDOMDocument :

<?xml version="1.0" encoding="UTF-8"?>
<Document>
    <empty/>
    <empty-2/>
    <non-empty>
Some text
</non-empty>
    <non-empty-2 some-attribute="attribute text">
        <empty-3/>
        <non-empty-3>
            <empty-4/>
            <empty-with-attribute another-attribute="some more text"/>
        </non-empty-3>
    </non-empty-2>
    <abc:non-empty-with-namespace xmlns:abc="urn:test:abc">
        <abc:empty-with-namespace abc:namespaced-attribute="namespaced attribute text"/>
    </abc:non-empty-with-namespace>
    <non-empty-comment>
        <!-- A comment -->
    </non-empty-comment>
    <non-empty-proc-instr>
        <?some-instruction?>
    </non-empty-proc-instr>
</Document>

, match, : contains('|list|of|element|names|', concat('|',name(),'|')). : |, | , . contains ( ) .

, non-empty, empty-2, empty-4 abc:empty-with-namespace :

<?xml version="1.0" encoding="utf-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
    <xsl:output method="xml" indent="yes"/>

    <xsl:template match="@* | node()">
        <xsl:copy>
            <xsl:apply-templates select="@* | node()"/>
        </xsl:copy>
    </xsl:template>

    <xsl:template match="*[contains('|non-empty|empty-2|empty-4|abc:empty-with-namespace|',  concat('|',name(),'|')) and not(*) and not(normalize-space()) and not(comment()) and not(processing-instruction())]">
        <xsl:element name="{name()}" namespace="{namespace-uri()}">
            <xsl:copy-of select="./@*"/>
        </xsl:element>
    </xsl:template>
</xsl:stylesheet>

FormatDOMDocument :

<?xml version="1.0" encoding="UTF-8"?>
<Document>
    <empty></empty>
    <empty-2/>
    <non-empty>
Some text
</non-empty>
    <non-empty-2 some-attribute="attribute text">
        <empty-3></empty-3>
        <non-empty-3>
            <empty-4/>
            <empty-with-attribute another-attribute="some more text"></empty-with-attribute>
        </non-empty-3>
    </non-empty-2>
    <abc:non-empty-with-namespace xmlns:abc="urn:test:abc">
        <abc:empty-with-namespace abc:namespaced-attribute="namespaced attribute text"/>
    </abc:non-empty-with-namespace>
    <non-empty-comment>
        <!-- A comment -->
    </non-empty-comment>
    <non-empty-proc-instr>
        <?some-instruction?>
    </non-empty-proc-instr>
</Document>

, , non-empty , , node ( , ). , empty , <empty></empty>, ( empty-3).