Search code examples
xsltxslt-1.0xslt-grouping

remove the Duplicate Elements from XML file and should not delete null values in XSLT file


I would appreciated if someone could help me to create xslt to remove duplicates nodes from XML based on duplicated element's value(PlayBack--ControlInfo-ControlName1) but not empty values.

I want to remove all the duplicate elements except null values(PlayBack--ControlInfo-ControlName1) from the GStep/Step

Input XML

<?xml version="1.0" encoding="utf-8"?>
      <Document>
       <Meta>
         <GpsFile>notepad_may_30_file</GpsFile>
         <GpsId>36fa4fe8-9691-4a7f-8bc1-9543f6b7d29a</GpsId>
          <ExePath>
             <ExePath1>C:\WINDOWS\SYSTEM32\notepad.exe</ExePath1>
          </ExePath>
        </Meta>
         <Process>
            <GStep DialogName="Untitled - Notepad">
             <Step DialogName="Untitled - Notepad">
              <Step-ID>3</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />      
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>4</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>5</Step-ID>      
              <PlayBack--ControlInfo-ControlName1>Edit</PlayBack--ControlInfo-ControlName1>     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>6</Step-ID>      
              <PlayBack--ControlInfo-ControlName1>Replace...\tCtrl+H</PlayBack--ControlInfo-ControlName1>     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>12</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>13</Step-ID>     
              <PlayBack--ControlInfo-ControlName1>Edit</PlayBack--ControlInfo-ControlName1>      
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>14</Step-ID>      
              <PlayBack--ControlInfo-ControlName1>Replace...\tCtrl+H</PlayBack--ControlInfo-ControlName1>      
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>15</Step-ID>     
              <PlayBack--ControlInfo-ControlName1>Cancel</PlayBack--ControlInfo-ControlName1>
            </Step>
          </GStep>
          <GStep DialogName="Replace">
             <Step DialogName="Replace">
                <Step-ID>8</Step-ID>     
                <PlayBack--ControlInfo-ControlName1 />      
             </Step>
             <Step DialogName="Replace">
                <Step-ID>9</Step-ID>      
                <PlayBack--ControlInfo-ControlName1>Cancel</PlayBack--ControlInfo-ControlName1>     
             </Step>
             <Step DialogName="Replace">
                <Step-ID>10</Step-ID>      
                <PlayBack--ControlInfo-ControlName1 />     
             </Step>
             <Step DialogName="Replace">
                <Step-ID>16</Step-ID>     
                <PlayBack--ControlInfo-ControlName1 />     
             </Step>
           </GStep>
         </Process>
       </Document>

Actually expecting a result like below.

<?xml version="1.0" encoding="utf-8"?>
      <Document>
       <Meta>
         <GpsFile>notepad_may_30_file</GpsFile>
         <GpsId>36fa4fe8-9691-4a7f-8bc1-9543f6b7d29a</GpsId>
          <ExePath>
             <ExePath1>C:\WINDOWS\SYSTEM32\notepad.exe</ExePath1>
          </ExePath>
        </Meta>
         <Process>
            <GStep DialogName="Untitled - Notepad">
             <Step DialogName="Untitled - Notepad">
              <Step-ID>3</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />      
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>4</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>5</Step-ID>      
              <PlayBack--ControlInfo-ControlName1>Edit</PlayBack--ControlInfo-ControlName1>     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>6</Step-ID>      
              <PlayBack--ControlInfo-ControlName1>Replace...\tCtrl+H</PlayBack--ControlInfo-ControlName1>     
            </Step>
            <Step DialogName="Untitled - Notepad">
              <Step-ID>12</Step-ID>     
              <PlayBack--ControlInfo-ControlName1 />     
            </Step>
             <Step DialogName="Untitled - Notepad">
              <Step-ID>15</Step-ID>     
              <PlayBack--ControlInfo-ControlName1>Cancel</PlayBack--ControlInfo-ControlName1>
            </Step>
          </GStep>
          <GStep DialogName="Replace">
             <Step DialogName="Replace">
                <Step-ID>8</Step-ID>     
                <PlayBack--ControlInfo-ControlName1 />      
             </Step>
             <Step DialogName="Replace">
                <Step-ID>9</Step-ID>      
                <PlayBack--ControlInfo-ControlName1>Cancel</PlayBack--ControlInfo-ControlName1>     
             </Step>
             <Step DialogName="Replace">
                <Step-ID>10</Step-ID>      
                <PlayBack--ControlInfo-ControlName1 />     
             </Step>
             <Step DialogName="Replace">
                <Step-ID>16</Step-ID>     
                <PlayBack--ControlInfo-ControlName1 />     
             </Step>
           </GStep>
         </Process>
       </Document>

Xslt code snippet.

<xsl:stylesheet version="1.0"
  xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  <xsl:output omit-xml-declaration="yes" indent="yes"/>
  <xsl:strip-space elements="*"/>
  <xsl:key name="ControlNameInfo1" match="Step" use="PlayBack--ControlInfo-ControlName1"/>
     <xsl:template match="node()|@*">
      <xsl:copy>
         <xsl:apply-templates select="node()|@*"/>
      </xsl:copy>
    </xsl:template>
   <xsl:template match="GStep/Step[not(generate-id() = generate-id(key('ControlNameInfo1', PlayBack-- 
        ControlInfo-ControlName)[1]))]"/>
        </xsl:stylesheet>

Should delete the duplicate values but should not delete empty PlayBack--ControlInfo-ControlName1

Thanks very much.


Solution

  • The XSLT 1.0 transcription of the XSLT 3 approach I posted to your previous question would be

    <xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
        version="1.0">
    
      <xsl:strip-space elements="*"/>
      <xsl:output indent="yes"/>
    
      <xsl:template match="@* | node()">
          <xsl:copy>
              <xsl:apply-templates select="@* | node()"/>
          </xsl:copy>
      </xsl:template>
    
      <xsl:key name="dups" match="Step[normalize-space(PlayBack--ControlInfo-ControlName)]" use="concat(generate-id(..), '|', PlayBack--ControlInfo-ControlName)"/>
    
      <xsl:template match="Step[normalize-space(PlayBack--ControlInfo-ControlName)][not(generate-id() = generate-id(key('dups', concat(generate-id(..), '|', PlayBack--ControlInfo-ControlName))[1]))]"/>
    
    </xsl:stylesheet>
    

    https://xsltfiddle.liberty-development.net/bEzkTcp/5