Finding all XML nodes between each two processing

问题:

Using XPath or XSLT 1.0, I need to find each node between processing instructions <?start?> and <?end?>. The following code:

//node()[preceding-sibling::processing-instruction()[self::processing-instruction('start')] 
following-sibling::processing-instruction()[ self::processing-instruction('end')]]`, 

works, but naturally, it only selects nodes between the first PI and the last PI. Is there any way how to select only the nodes that are between each start - end pair?

<root>
    abc

<?start?>def<Highlighted
    bold="yes"><Highlighted italic="yes">ghi</Highlighted></Highlighted>jkl
    <?pi?>
    <table>
      <Caption>stu</Caption>
    </table>vw

<?end?>
xy<?start?> 
abc <Caption>def</Caption> ghi<?end?> jkl
</root>

回答1:

Here is an XSLT 2.0 example that uses for-each-group group-starting-with/group-ending-with to find and output the nodes between those pairs of processing instructions:

<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema"
    exclude-result-prefixes="xs"
    version="2.0">

<xsl:output indent="yes"/>

<xsl:template match="root">
    <xsl:for-each-group select="node()" group-starting-with="processing-instruction('start')">
        <xsl:if test="self::processing-instruction('start')">
            <group>
                <xsl:for-each-group select="current-group() except ." group-ending-with="processing-instruction('end')">
                    <xsl:sequence select="current-group()[position() ne last()]"/>
                </xsl:for-each-group>
            </group>
        </xsl:if>
    </xsl:for-each-group>
</xsl:template>

</xsl:stylesheet>

Result for your sample is

<group>def<Highlighted bold="yes">
      <Highlighted italic="yes">ghi</Highlighted>
   </Highlighted>jkl
    <?pi?>
    <table>
        <Caption>stu</Caption>
    </table>vw

    </group>
<group> 
    abc <Caption>def</Caption> ghi</group>

Using XSLT 1.0 you can compute the intersection of nodes following the start pi and preceding the end pi:

<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    version="1.0">

    <xsl:output indent="yes"/>

    <xsl:key name="start" match="root/node()[not(self::processing-instruction('start'))]" use="generate-id(preceding-sibling::processing-instruction('start')[1])"/>
    <xsl:key name="end" match="root/node()[not(self::processing-instruction('end'))]" use="generate-id(following-sibling::processing-instruction('end')[1])"/>

    <xsl:template match="root">
        <xsl:apply-templates select="processing-instruction('start')"/>
    </xsl:template>

    <xsl:template match="processing-instruction('start')">
        <xsl:variable name="end" select="following-sibling::processing-instruction('end')[1]"/>
        <xsl:variable name="following-start" select="key('start', generate-id())"/>
        <xsl:variable name="preceding-end" select="key('end', generate-id($end))"/>
        <xsl:variable name="intersect" select="$following-start[count(. | $preceding-end) = count($preceding-end)]"/>
        <group>
            <xsl:copy-of select="$intersect"/>
        </group>
    </xsl:template>
</xsl:stylesheet>