开发者

XSLT modify identity rule with string matching

I need to create an XSLT to follow two rules (in order of priority):

  1. Should copy the entire /xs:schema/node() in which /xs:schema/node()/@name starts with "prefix_". This /xs:schema/node() should include all the descendants and attributes.
  2. Should create a /xs:schema/node() containing only the descendants with any attribute that starts with "prefix_"

The document I have follows this format

<?xml version="1.0" encoding="UTF-8"?>
<!--
    this is
    a really long
    comment
    that spans
    multiple lines
-->
<!-- <!a comment > another comment -->
<!-- <!a comment > another comment -->
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" elementFormDefault="unqu开发者_如何学编程alified"
    attributeFormDefault="unqualified">

    <!-- a comment -->
    <xs:node name="ABC">
        <xs:node>
            <xs:element/>
            <xs:element attr="asdf"/>
        </xs:node>
    </xs:node>
    <!-- <!a comment > another comment -->
    <node name="DEF">
        <element/>
        <element attr="asdf" bttr="zxcv"/>
    </node>
    <!-- <!a comment > another comment -->
    <node name="prefix_a">
        <element/>
        <element attr="asdf"/>
        <element attr="prefix_attr"/>
        <element battr="prefix_battr"/>
    </node>

    <node name="prefix_b">
        <node>
            <element/>
            <element battr="prefix_bttr"/>
            <element hattr="prefix_cattr"/>
        </node>
    </node>

    <node name="c">
        <node>
            <node>
                <node>
                    <node>
                        <element attr="qwerty"/>
                        <element attr="zxvc"/>
                        <element attr="asdf"/>
                        <element battr="prefix_bttr"/>
                        <element flattr="prefix_hattr"/>
                    </node>
                </node>
            </node>
        </node>
    </node>

    <node name="d">
        <element/>
        <element attr="asdf"/>
        <element shattr="prefix_shattr"/>
        <element cattr="prefix_battr"/>
    </node>
    <!-- <!a comment > another comment -->
    <node name="g">
        <element attr="asdf" bttr="zxcv"/>
        <element/>
    </node>

</xs:schema>

The XSLT should return;

<xml>
<xs:schema>

  <node name="prefix_a">
    <element />
    <element attr="asdf" />
    <element attr="prefix_attr" />
    <element battr="prefix_battr" />
  </node>

  <node name="prefix_b">
    <node>
      <element />
      <element battr="prefix_bttr" />
      <element hattr="prefix_cattr" />
    </node>
  </node>

  <node name="c">
    <node>
      <node>
        <node>
          <node>
            <element battr="prefix_bttr" />
            <element flattr="prefix_hattr" />
          </node>
        </node>
      </node>
    </node>
  </node>

  <node name="d">
    <element shattr="prefix_shattr" />
    <element cattr="prefix_battr" />
  </node>

</xs:schema>

I am using the following XSLT below;

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsd="http://www.w3.org/2001/XMLSchema">

    <xsl:namespace-alias stylesheet-prefix="xs" result-prefix="xsd"/>

    <xsl:output method="xml" indent="yes"/>
    <xsl:strip-space elements="*"/>

    <xsl:template match="/">
        <xsl:apply-templates select="xsd:schema"/>
    </xsl:template>

    <xsl:template match="xsd:schema">
        <xs:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" elementFormDefault="unqualified"
            attributeFormDefault="unqualified" version="1.0">
            <xsl:apply-templates select="node()[starts-with(@name, 'prefix_')]"/>
            <xsl:apply-templates select="node()[descendant::node()/@*[starts-with(., 'prefix_')]]"/>
        </xs:schema>
    </xsl:template>

    <xsl:template match="xsd:schema/node()[starts-with(@name, 'prefix_')]">
        <xsl:copy-of select="current()"/>
    </xsl:template>

    <xsl:template match="xsd:schema/node()[descendant::node()/@*[starts-with(., 'prefix_')]]">
        <xsl:copy-of select="current()"/>
    </xsl:template>


</xsl:stylesheet>


I have fixed the silly error noticed by @Dimitre.

Now, the following transform:

 <xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" 
    xmlns:xs="http://www.w3.org/2001/XMLSchema">
    <xsl:output method="xml" indent="yes"/>

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

    <xsl:template match="xs:schema/*[
        not(starts-with(@name,'prefix_'))
            and
            not(.//*/@*[starts-with(.,'prefix_')])]"/>

    <xsl:template match="*[
        not(*) 
            and
        not(@*[starts-with(.,'prefix_')])
            and
        not(ancestor::*[starts-with(@name,'prefix_')])
        ]"/>

</xsl:stylesheet>

given this input (slightly modified to cover much more complex cases):

<xml>
    <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">

        <!-- a comment -->

        <node name="prefix_a">
            <element />
            <element attr="asdf" />
            <element x="y" attr="prefix_attr" />
            <element battr="prefix_battr" y="x"/>
        </node>

        <node name="prefix_b">
            <node>
                <element />
                <element battr="prefix_bttr" />
                <element hattr="prefix_cattr" />
            </node>
        </node>

        <node name="c">
            <node>
                <node>
                    <node>
                        <node>
                            <element attr="qwerty" />
                            <element attr="zxvc" />
                            <element attr="asdf" />
                            <element battr="prefix_bttr" x="y"/>
                            <element flattr="prefix_hattr" y="x"/>
                        </node>
                    </node>
                </node>
            </node>
        </node>

        <node name="d">
            <element />
            <element attr="asdf" />
            <element shattr="prefix_shattr" />
            <element cattr="prefix_battr" />
        </node>

        <node name="e">
            <element />
            <element attr="asdf" />
        </node>

    </xs:schema>
</xml>

produces:

<xml>
   <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
      <node name="prefix_a">
         <element/>
         <element attr="asdf"/>
         <element x="y" attr="prefix_attr"/>
         <element battr="prefix_battr" y="x"/>
      </node>
      <node name="prefix_b">
         <node>
            <element/>
            <element battr="prefix_bttr"/>
            <element hattr="prefix_cattr"/>
         </node>
      </node>
      <node name="c">
         <node>
            <node>
               <node>
                  <node>
                     <element battr="prefix_bttr" x="y"/>
                     <element flattr="prefix_hattr" y="x"/>
                  </node>
               </node>
            </node>
         </node>
      </node>
      <node name="d">
         <element shattr="prefix_shattr"/>
         <element cattr="prefix_battr"/>
      </node>
   </xs:schema>
</xml>


In the case of the nodes that which have a @name attribute starting with prefix_ you can leave the identity transform to do its work. So, you only need to override the case for elements who don't have a @name starting with prefix_.

<xsl:template match="xs:schema/node()[not(starts-with(@name, 'prefix'))]">

To copy only the descendants with any attribute that starts with "prefix_", you will also need to copy any node that may not have an attribute itself, but does itself have a descendant meeting the criteria.

<xsl:apply-templates 
   select="@*|
      node()[descendant-or-self::*[count(@*[starts-with(., 'prefix')]) &gt; 0]]" 
   mode="attr" />

So, here, you use the mode attribute when you apply the templates, so you can override the behaviour on matching the descendants too

<xsl:template match="@*|node()" mode="attr">

Here is the full XSLT:

<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:xs="http://www.w3.org/2001/XMLSchema">
   <xsl:output method="xml" indent="yes"/>

   <xsl:template match="/">
      <xsl:apply-templates />
   </xsl:template>

   <xsl:template match="xs:schema/node()[not(starts-with(@name, 'prefix'))]">
      <xsl:if test="descendant-or-self::*[count(@*[starts-with(., 'prefix')]) &gt; 0]">
         <xsl:copy>
            <xsl:apply-templates select="@*|node()[descendant-or-self::*[count(@*[starts-with(., 'prefix')]) &gt; 0]]" mode="attr" />
         </xsl:copy>
      </xsl:if>
   </xsl:template>

   <xsl:template match="@*|node()" mode="attr">
      <xsl:copy>
         <xsl:apply-templates select="@*[starts-with(., 'prefix')]|node()[descendant-or-self::*[count(@*[starts-with(., 'prefix')]) &gt; 0]]" mode="attr"/>
      </xsl:copy>
   </xsl:template>

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

</xsl:stylesheet>

When applied to your input XML, the output is as follows:

<xml>
   <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
      <node name="prefix_a">
         <element/>
         <element attr="asdf"/>
         <element attr="prefix_attr"/>
         <element battr="prefix_battr"/>
      </node>
      <node name="prefix_b">
         <node>
            <element/>
            <element battr="prefix_bttr"/>
            <element hattr="prefix_cattr"/>
         </node>
      </node>
      <node name="c">
         <node>
            <node>
               <node>
                  <node>
                     <element battr="prefix_bttr"/>
                     <element flattr="prefix_hattr"/>
                  </node>
               </node>
            </node>
         </node>
      </node>
      <node name="d">
         <element shattr="prefix_shattr"/>
         <element cattr="prefix_battr"/>
      </node>
   </xs:schema>
</xml>


None of the other two answers works correctly if the attribute whose value starts with "prefix_" isn't the first (and only) attribute of its parent element!

This transformation (besides correct seems to be the shortest and simplest -- no modes and no explicit conditional instructions):

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

 <xsl:template match=
   "node[@name[not(starts-with(.,'prefix_'))]
        and
          not(descendant::*[@*[starts-with(.,'prefix_')]])
         ]"/>

  <xsl:template match=
   "*[ancestor::node[@name[not(starts-with(.,'prefix_'))]]
    and
      not(*)
    and
      not(@*[starts-with(.,'prefix_')])
     ]"/>
</xsl:stylesheet>

when applied on the following XML document (the provided one, but extended so that some elements have two attributes -- look at <node name="c">):

<xml>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">

  <!-- a comment -->

  <node name="prefix_a">
    <element />
    <element attr="asdf" />
    <element attr="prefix_attr" />
    <element battr="prefix_battr" />
  </node>

  <node name="prefix_b">
    <node>
      <element />
      <element battr="prefix_bttr" />
      <element hattr="prefix_cattr" />
    </node>
  </node>

  <node name="c">
    <node>
      <node>
        <node>
          <node>
            <element attr="qwerty" />
            <element attr="zxvc" />
            <element attr="asdf" />
            <element battr="prefix_bttr" />
            <element flattr="prefix_hattr" />
          </node>
        </node>
      </node>
    </node>
  </node>

  <node name="d">
    <element />
    <element attr="asdf" />
    <element shattr="prefix_shattr" />
    <element cattr="prefix_battr" />
  </node>

  <node name="e">
    <element />
    <element attr="asdf" />
  </node>
</xs:schema>
</xml>

produces the wanted, correct result:

<xml>
   <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"><!-- a comment --><node name="prefix_a">
         <element/>
         <element attr="asdf"/>
         <element attr="prefix_attr"/>
         <element battr="prefix_battr"/>
      </node>
      <node name="prefix_b">
         <node>
            <element/>
            <element battr="prefix_bttr"/>
            <element hattr="prefix_cattr"/>
         </node>
      </node>
      <node name="c">
         <node>
            <node>
               <node>
                  <node>
                     <element y="z" battr="prefix_bttr"/>
                     <element x="y" flattr="prefix_hattr"/>
                  </node>
               </node>
            </node>
         </node>
      </node>
      <node name="d">
         <element shattr="prefix_shattr"/>
         <element cattr="prefix_battr"/>
      </node>
   </xs:schema>
</xml>

Do note that the solutions in the other two answers lose either the element <node name="c"> and its complete subtree, or lose some of the attributes.

0

上一篇:

下一篇:

精彩评论

暂无评论...
验证码 换一张
取 消

最新问答

问答排行榜