Generate/get xpath from XML node java

Update:

@c0mrade has updated his question. Here is a solution to it:

This XSLT transformation:

<xsl:stylesheet version="1.0"  xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output method="text"/>
    <xsl:strip-space elements="*"/>

    <xsl:variable name="vApos">'</xsl:variable>

    <xsl:template match="*[@* or not(*)] ">
      <xsl:if test="not(*)">
         <xsl:apply-templates select="ancestor-or-self::*" mode="path"/>
         <xsl:value-of select="concat('=',$vApos,.,$vApos)"/>
         <xsl:text>&#xA;</xsl:text>
        </xsl:if>
        <xsl:apply-templates select="@*|*"/>
    </xsl:template>

    <xsl:template match="*" mode="path">
        <xsl:value-of select="concat("https://stackoverflow.com/",name())"/>
        <xsl:variable name="vnumPrecSiblings" select=
         "count(preceding-sibling::*[name()=name(current())])"/>
        <xsl:if test="$vnumPrecSiblings">
            <xsl:value-of select="concat('[', $vnumPrecSiblings +1, ']')"/>
        </xsl:if>
    </xsl:template>

    <xsl:template match="@*">
        <xsl:apply-templates select="../ancestor-or-self::*" mode="path"/>
        <xsl:value-of select="concat('[@',name(), '=',$vApos,.,$vApos,']')"/>
        <xsl:text>&#xA;</xsl:text>
    </xsl:template>
</xsl:stylesheet>

when applied on the provided XML document:

<root>
    <elemA>one</elemA>
    <elemA attribute1='first' attribute2='second'>two</elemA>
    <elemB>three</elemB>
    <elemA>four</elemA>
    <elemC>
        <elemB>five</elemB>
    </elemC>
</root>

produces exactly the wanted, correct result:

/root/elemA='one'
/root/elemA[2]='two'
/root/elemA[2][@attribute1='first']
/root/elemA[2][@attribute2='second']
/root/elemB='three'
/root/elemA[3]='four'
/root/elemC/elemB='five'

When applied to the newly-provided document by @c0mrade:

<root>
    <elemX serial="kefw90234kf2esda9231">
        <id>89734</id>
    </elemX>
</root>

again the correct result is produced:

/root/elemX='89734'
/root/elemX[@serial="kefw90234kf2esda9231"]

Explanation:

  • Only elements that have no children elements, or have attributes are matched and processed.

  • For any such element, if it doesn’t have children-elements all of its ancestor-or self elements are processed in a specific mode, named 'path'. Then the "='theValue'" part is output and then a NL character.

  • All attributes of the matched element are then processed.

  • Then finally, templates are applied to all children-elements.

  • Processing an element in the 'path' mode is simple: A / character and the name of the element are output. Then, if there are preceding siblings with the same name, a “[numPrecSiblings+1]` part is output.

  • Processing of attributes is simple: First all ancestor-or-self:: elements of its parent are processed in 'path' mode, then the [attrName=attrValue] part is output, followed by a NL character.

Do note:

  • Names that are in a namespace are displayed without any problem and in their initial readable form.

  • To aid readability, an index of [1] is never displayed.


Below is my initial answer (may be ignored)

Here is a pure XSLT 1.0 solution:

Below is a sample xml document and a stylesheet that takes a node-set parameter and produces one valid XPath expression for every member-node.

stylesheet (buildPath.xsl):


<xsl:stylesheet version='1.0'
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:msxsl="urn:schemas-microsoft-com:xslt" 
>

<xsl:output method="text"/>
<xsl:variable name="theParmNodes" select="//namespace::*[local-name() =
'myNamespace']"/>
<xsl:template match="https://stackoverflow.com/">
  <xsl:variable name="theResult">
    <xsl:for-each select="$theParmNodes">
    <xsl:variable name="theNode" select="."/>
    <xsl:for-each select="$theNode |
$theNode/ancestor-or-self::node()[..]">
      <xsl:element name="slash">/</xsl:element>
      <xsl:choose>
        <xsl:when test="self::*">           
          <xsl:element name="nodeName">
            <xsl:value-of select="name()"/>
            <xsl:variable name="thisPosition" 
                select="count(preceding-sibling::*[name(current()) = 
                        name()])"/>
            <xsl:variable name="numFollowing" 
                select="count(following-sibling::*[name(current()) = 
                        name()])"/>
            <xsl:if test="$thisPosition + $numFollowing > 0">
              <xsl:value-of select="concat('[', $thisPosition +
                                                           1, ']')"/>
            </xsl:if>
          </xsl:element>
        </xsl:when>
        <xsl:otherwise> <!-- This node is not an element -->
          <xsl:choose>
            <xsl:when test="count(. | ../@*) = count(../@*)">   
            <!-- Attribute -->
              <xsl:element name="nodeName">
                <xsl:value-of select="concat('@',name())"/>
              </xsl:element>
            </xsl:when>     
            <xsl:when test="self::text()">  <!-- Text -->
              <xsl:element name="nodeName">
                <xsl:value-of select="'text()'"/>
                <xsl:variable name="thisPosition" 
                          select="count(preceding-sibling::text())"/>
                <xsl:variable name="numFollowing" 
                          select="count(following-sibling::text())"/>
                <xsl:if test="$thisPosition + $numFollowing > 0">
                  <xsl:value-of select="concat('[', $thisPosition + 
                                                           1, ']')"/>
                </xsl:if>
              </xsl:element>
            </xsl:when>     
            <xsl:when test="self::processing-instruction()">
            <!-- Processing Instruction -->
              <xsl:element name="nodeName">
                <xsl:value-of select="'processing-instruction()'"/>
                <xsl:variable name="thisPosition" 
                   select="count(preceding-sibling::processing-instruction())"/>
                <xsl:variable name="numFollowing" 
                    select="count(following-sibling::processing-instruction())"/>
                <xsl:if test="$thisPosition + $numFollowing > 0">
                  <xsl:value-of select="concat('[', $thisPosition + 
                                                            1, ']')"/>
                </xsl:if>
              </xsl:element>
            </xsl:when>     
            <xsl:when test="self::comment()">   <!-- Comment -->
              <xsl:element name="nodeName">
                <xsl:value-of select="'comment()'"/>
                <xsl:variable name="thisPosition" 
                         select="count(preceding-sibling::comment())"/>
                <xsl:variable name="numFollowing" 
                         select="count(following-sibling::comment())"/>
                <xsl:if test="$thisPosition + $numFollowing > 0">
                  <xsl:value-of select="concat('[', $thisPosition + 
                                                            1, ']')"/>
                </xsl:if>
              </xsl:element>
            </xsl:when>     
            <!-- Namespace: -->
            <xsl:when test="count(. | ../namespace::*) = 
                                               count(../namespace::*)">

              <xsl:variable name="apos">'</xsl:variable>
              <xsl:element name="nodeName">
                <xsl:value-of select="concat('namespace::*', 
                '[local-name() = ', $apos, local-name(), $apos, ']')"/>

              </xsl:element>
            </xsl:when>     
          </xsl:choose>
        </xsl:otherwise>            
      </xsl:choose>
    </xsl:for-each>
    <xsl:text>&#xA;</xsl:text>
  </xsl:for-each>
 </xsl:variable>
 <xsl:value-of select="msxsl:node-set($theResult)"/>
</xsl:template>
</xsl:stylesheet>

xml source (buildPath.xml):


<!-- top level Comment -->
<root>
    <nodeA>textA</nodeA>
 <nodeA id="nodeA-2">
  <?myProc ?>
        xxxxxxxx
  <nodeB/>
        <nodeB xmlns:myNamespace="myTestNamespace">
  <!-- Comment within /root/nodeA[2]/nodeB[2] -->
   <nodeC/>
  <!-- 2nd Comment within /root/nodeA[2]/nodeB[2] -->
        </nodeB>
        yyyyyyy
  <nodeB/>
  <?myProc2 ?>
    </nodeA>
</root>
<!-- top level Comment -->

Result:

/root/nodeA[2]/nodeB[2]/namespace::*[local-name() = 'myNamespace']
/root/nodeA[2]/nodeB[2]/nodeC/namespace::*[local-name() =
'myNamespace']

Leave a Comment