Search code examples
xmlxsltsaxon

Result of one xslt transformation is input for the another one


I'm a beginner in xslt , so don't mind me asking the basic questions. I would like to use the result of the first transformation level as an input for the another one. The input for the first transformation is a target.xml file, which includes subscribers ("aries","cas"...):

<subscription-table>
        <subscriber name="aries" useZipXfer="yes" usePubMed="no">
            <ftp server="dummy.url1.com" port="21" remotedir="/XXXXXXX" userid="XXXXXXX" password="XXXXXXXXX" binary="yes" passive="no"/>
            <notify-success>
                <mail mailhost="smtprelayptc1.test.net" mailport="25" subject="MRCS-PS HEADER UPDATE - PAP">
                    <from address="success1.from@mail.com"/>
                    <to address="success1.to@mail.com"/>
                </mail>
            </notify-success>
            <notify-failure>
                <mail mailhost="smtprelayptc1.test.net" mailport="25" subject="MRCS-PS HEADER UPDATE - PAP">
                    <from address="failure1.from@mail.com"/>
                    <to address="failure1.to@mail.com"/>
                </mail>
            </notify-failure>
        </subscriber>
        <subscriber name="cas" useZipXfer="no" usePubMed="yes" sendPromote="no">
            <ftp server="dummy.url2.com" port="21" remotedir="/YYYYYYY" userid="YYYYYYY" password="YYYYYYYYY" binary="yes" passive="no"/>
            <notify-success>
                <mail mailhost="smtprelayptc1.test.net" mailport="25" subject="MRCS-PS HEADER UPDATE - PAP">
                    <from address="success2.from@mail.com"/>
                    <to address="success2.to@mail.com"/>
                </mail>
            </notify-success>
            <notify-failure>
                <mail mailhost="smtprelayptc1.test.net" mailport="25" subject="MRCS-PS HEADER UPDATE - PAP">
                    <from address="failure2.from@mail.com"/>
                    <to address="failure2.to@mail.com"/>
                </mail>
            </notify-failure>
        </subscriber>
</subscription-table>

Each subscriber has its own file (aries_subscriptions.xml, cas_subscriptions.xml...). The subscriptions files include journals. For example, aries_subscriptions.xml is:

<subscription>
     <database status="update" name="ovftdb">        
         <journal status="*" name="00002030" >
             <issue status="new" pubdate="01/01/2004" name="*" an="99999999-999999999-99999" >
                 <header/>
             </issue>
         </journal>      
         <journal status="*" name="00000374" >
             <issue status="new" pubdate="01/01/2004" name="*" an="99999999-999999999-99999" >
                 <header/>
             </issue>
         </journal>      
         <journal status="*" name="00000372" >
             <issue status="new" pubdate="01/01/2004" name="*" an="99999999-999999999-99999" >
                 <header/>
             </issue>
         </journal>
...

I need to generate the third file, lookup.xml, which can have repeated journals, depend on subscribers (subscriber is in the attribute "identifier"):

<?xml version="1.0" encoding="UTF-8"?>
<journals xmlns:xlink="http://www.w3.org/1999/xlink">
        <journal name="00002030">
            <target identifier="aries" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00000372">
            <target identifier="aries" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00002030">
            <target identifier="cas" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00000372">
            <target identifier="cas" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
    </journals>

I would like to use xslt code, which creates repeated journals, and generate the document that have unique journals, with all its nested subscribers. The desired document would be:

<?xml version="1.0" encoding="UTF-8"?>
<journals xmlns:xlink="http://www.w3.org/1999/xlink"
    <journal name="00002030">
       <target identifier="aries" pubdate="01/01/2004">
          <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
       </target>
       <target identifier="cas" pubdate="01/01/2004">
          <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
       </target>
    </journal>
    <journal name="00000372">
       <target identifier="aries" pubdate="01/01/2004">
          <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
       </target>
       <target identifier="cas" pubdate="01/01/2004">
          <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
       </target>
    </journal>  
</journals>

The first part of xslt, which creates duplicated journals, is:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="2.0"
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema" 
    xmlns:xlink="http://www.w3.org/1999/xlink"      
    xmlns:saxon="http://saxon.sf.net/"
    exclude-result-prefixes="xs xsl saxon xlink">


    <xsl:strip-space elements="*" />    

    <xsl:include href="utilities.xsl" />
    <xsl:include href="assetTargetToLookupRemoveDuplicates.xsl"/>

    <xsl:variable name="inputFolderAndFile">
        <xsl:call-template
            name="getValuesBeforeAndAfterLastOccurance">
            <xsl:with-param name="inputString"
                select="string(base-uri(.))" />
            <xsl:with-param name="char" select="'/'" />
        </xsl:call-template>
    </xsl:variable>

    <xsl:variable name="inputFolderPath"
        select="substring-before($inputFolderAndFile, '*')" />
    <xsl:variable name="inputFile"
        select="substring-after($inputFolderAndFile, '*')" />
    <xsl:variable name="tokens"
        select="tokenize($inputFile,'\.')" />
    <xsl:variable name="baseFileName"
        select="string-join($tokens[not(.=$tokens[last()])], '.')" />

    <xsl:template match="@* | * | comment() | processing-instruction()">
        <xsl:apply-templates select="@* | node()" mode="package"/>
    </xsl:template>

    <xsl:template match="text()" mode="package">
        <xsl:copy/> 
    </xsl:template>     

    <xsl:template match="/" mode="package">
        <xsl:result-document method="xml" omit-xml-declaration="no" indent="yes" encoding="UTF-8" href="lookup.xml">
            <xsl:variable name="initialOutput">             
                <xsl:apply-templates mode="package"/>               
            </xsl:variable>                                             
            <xsl:apply-templates select="$initialOutput" mode="remove-duplicates"/>                        
        </xsl:result-document>
    </xsl:template> 

    <xsl:template match="subscriber" mode="package">
        <xsl:variable name="subscriberName" select="document(concat($inputFolderPath, '/', @name,'_subscriptions.xml'))" />
        <xsl:element name="journals" namespace="http://www.w3.org/1999/xlink">      
            <xsl:apply-templates select="$subscriberName" mode="journal-processing"/>
        </xsl:element>      
    </xsl:template>

    <xsl:template match="journal" mode="journal-processing">
        <xsl:variable name="journalName" select="@name" />
        <xsl:variable name="journalPubDate" select="issue/@pubdate" />
        <xsl:variable name="subscriberNameFromDoc" select="substring-before(tokenize(base-uri(), '/')[last()], '_subscriptions')" />

        <xsl:element name="journal">
            <xsl:attribute name="name" select="$journalName"/>
            <xsl:element name="target">
                <xsl:attribute name="identifier" select="$subscriberNameFromDoc"/>
                <xsl:attribute name="pubdate" select="$journalPubDate"/>
                <xsl:element name="targetLink">                                                            
                    <xsl:attribute name="xlink:href">targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])</xsl:attribute>                    
                    <xsl:attribute name="xlink:href" select="targets.xml#//descendant::subscriber[attribute::name='$subscriberNameFromDoc']"/> -->
                </xsl:element>
            </xsl:element>
        </xsl:element>

    </xsl:template>
</xsl:stylesheet>

I want to use $initialOutput variable to provide the result of the first transformation to the next one. In the second transformation, assetTargetToLookupRemoveDuplicates.xsl, I have the following code:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema" 
    xmlns:xlink="http://www.w3.org/1999/xlink"  
    xmlns:saxon="http://saxon.sf.net/"
    exclude-result-prefixes="xlink xs xsl saxon"
    version="2.0">


    <xsl:strip-space elements="*" />

    <xsl:template match="/" mode="remove-duplicates">       
        <xsl:apply-templates select="journals" mode="remove-duplicates"/>
    </xsl:template>

    <xsl:template match="journals" mode="remove-duplicates">
        <xsl:copy>
            <xsl:for-each-group select="journal" group-by="@name">
                <xsl:copy>
                    <xsl:copy-of select="@*"/>
                    <xsl:copy-of select="current-group()/target"/>
                </xsl:copy>
            </xsl:for-each-group>
        </xsl:copy>
    </xsl:template>

</xsl:stylesheet>

The second transformation doesn't transform the duplicate journals to unique ones. The result of the whole process is the document with duplicate journals. The result is, again:

<?xml version="1.0" encoding="UTF-8"?>
<journals xmlns:xlink="http://www.w3.org/1999/xlink">
        <journal name="00002030">
            <target identifier="aries" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00000372">
            <target identifier="aries" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00002030">
            <target identifier="cas" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
        <journal name="00000372">
            <target identifier="cas" pubdate="01/01/2004">
                <targetLink xmlns:xlink="http://www.w3.org/1999/xlink"
              xlink:href="targets.xml#xpointer(/descendant::subscriber[attribute::name='$subscriberNameFromDoc'])"/>
            </target>
        </journal>
    </journals>

Could you please help me to find out why the second transformation works that way? Thank you in advance for any help.


Solution

  • Thanks to Martin's comments and help, I finally fixed the solution. The following code does the things I described in my question:

    <?xml version="1.0" encoding="UTF-8"?>
    <xsl:stylesheet version="2.0"
        xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
        xmlns:xs="http://www.w3.org/2001/XMLSchema" 
        xmlns:xlink="http://www.w3.org/1999/xlink"      
        xmlns:saxon="http://saxon.sf.net/"      
        exclude-result-prefixes="xs xsl saxon xlink">
    
        <xsl:strip-space elements="*" />
    
        <xsl:output method="xml" omit-xml-declaration="no"
            indent="yes" encoding="UTF-8" saxon:character-representation="entity" />
    
        <xsl:include href="utilities.xsl" />    
    
        <xsl:variable name="inputFolderAndFile">
            <xsl:call-template
                name="getValuesBeforeAndAfterLastOccurance">
                <xsl:with-param name="inputString"
                    select="string(base-uri(.))" />
                <xsl:with-param name="char" select="'/'" />
            </xsl:call-template>
        </xsl:variable>
    
        <xsl:variable name="inputFolderPath"
            select="substring-before($inputFolderAndFile, '*')" />
        <xsl:variable name="inputFile"
            select="substring-after($inputFolderAndFile, '*')" />
        <xsl:variable name="tokens"
            select="tokenize($inputFile,'\.')" />
        <xsl:variable name="baseFileName"
            select="string-join($tokens[not(.=$tokens[last()])], '.')" />
    
        <xsl:template match="@* | * | comment() | processing-instruction()">    
            <xsl:apply-templates select="@* | node()"/> 
        </xsl:template>
    
        <xsl:template match="text()" >
            <xsl:copy/> 
        </xsl:template>     
    
    
        <xsl:template match="/">        
            <xsl:variable name="initialOutput">
                <xsl:element name="journals">
                    <xsl:namespace name="xlink" select="'http://www.w3.org/1999/xlink'"/>       
                    <xsl:apply-templates/>
                </xsl:element>          
            </xsl:variable>                                                                     
            <xsl:apply-templates select="$initialOutput" mode="remove-duplicates"/>  
        </xsl:template> 
    
        <xsl:template match="subscriber">       
            <xsl:variable name="subscriberName" select="document(concat($inputFolderPath, '/', @name,'_subscriptions.xml'))" />     
            <xsl:apply-templates select="$subscriberName" mode="journal-processing"/>       
        </xsl:template>
    
        <xsl:template match="journal" mode="journal-processing">
            <xsl:variable name="journalName" select="@name" />
            <xsl:variable name="journalPubDate" select="issue/@pubdate" />
            <xsl:variable name="subscriberNameFromDoc" select="substring-before(tokenize(base-uri(), '/')[last()], '_subscriptions')" />
    
            <xsl:element name="journal">
                <xsl:attribute name="name" select="$journalName"/>
                <xsl:element name="target">
                    <xsl:attribute name="identifier" select="$subscriberNameFromDoc"/>
                    <xsl:attribute name="pubdate" select="$journalPubDate"/>
                    <xsl:element name="targetLink" namespace="http://www.w3.org/1999/xlink">
                                            <xsl:variable name="apostrophe">'</xsl:variable>                
                        <xsl:attribute name="xlink:href" select="concat('targets.xml','#','xpointer(/descendant::subscriber[attribute::name=',$apostrophe,$subscriberNameFromDoc,$apostrophe,'])')"/>
                    </xsl:element>
                </xsl:element>
            </xsl:element>
    
        </xsl:template> 
    
        <xsl:template match="/" mode="remove-duplicates">           
            <xsl:apply-templates select="journals" mode="remove-duplicates"/>
        </xsl:template>
    
        <xsl:template match="journals" mode="remove-duplicates">                    
            <xsl:copy>
                <xsl:for-each-group select="journal" group-by="@name">
                    <xsl:copy>
                        <xsl:copy-of select="@*"/>
                        <xsl:copy-of select="current-group()/target"/>
                    </xsl:copy>
                </xsl:for-each-group>
            </xsl:copy>
        </xsl:template>
    </xsl:stylesheet>