如何使这个XSLT消除转换专门针对不同的节点父节点？

Question

XSLT：

<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output indent="yes"/>
    <xsl:strip-space elements="*"/>

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

    <xsl:template match="*[*][deep-equal(.,preceding::*[name()=current()/name()][@id=current()/@id][1])]"/>
</xsl:stylesheet>

应用于我的输入时：

<myroot>
    <nodeA id="a">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                <somechild>a</somechild>
            </item1>
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
            <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>
</myroot>

给我正确的输出：

<myroot>
    <nodeA id="a">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>
</myroot>

* 但问题是当我有另一个nodeA具有不同的id时，它会将这两个节点视为一个*

第二个输入示例：

<myroot>
    <nodeA id="a">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                <somechild>a</somechild>
            </item1>
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
            <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>

    <nodeA id="b">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                <somechild>a</somechild>
            </item1>
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
            <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>
</myroot>

我的输出：

<myroot>
   <nodeA id="a">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
         <item1 id="1" method="create">
            <otherchild>a</otherchild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this --><somechild>bbb</somechild>
         </item1>
         <item1 id="3" method="create">
            <other>xx</other>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
   <nodeA id="b">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this --><somechild>bbb</somechild>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
</myroot>

预期输出应为：

<myroot>
    <nodeA id="a">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>

    <nodeA id="b">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>
</myroot>

我应该在XSLT文件上添加什么内容，使其适用于两个或更多节点父nodeA或nodeB等。

• 目标是使用successive duplicate删除节点 相同的元素名称item1 item2等，相同的id和相同的method。

• XML节点后跟其他具有完全same element name，same id，same method和same children的节点将被视为重复。

• 如果被比较的两个节点没有共享相同的'nodeA'级别 节点，那么它们不应被视为要删除的重复项

由于 约翰

Answer 1

此转化：

<xsl:stylesheet version="2.0"
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema">
    <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=
   "section/*
      [for $current in .,
           $curNodeAnc in $current/ancestor::*[starts-with(name(), 'node')][1]
         return
           some $preceding in $current/preceding::*
              satisfies
                 $preceding/parent::section
                and
                 $curNodeAnc is $preceding/ancestor::*[starts-with(name(), 'node')][1]
                and
                 deep-equal($current, $preceding)

      ]
   "/>
</xsl:stylesheet>

应用于提供的XML文档：

<myroot>
        <nodeA id="a">
            <section id="i">
                <item1 id="0" method="create">
                    <somechild>a</somechild>
                </item1>

                <item1 id="1" method="create">
                    <otherchild>a</otherchild>
                </item1>
            </section>

            <section id="i">
                <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                    <somechild>a</somechild>
                </item1>
                <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                    <somechild>bbb</somechild>
                </item1>
                <item1 id="3" method="create">
                    <other>xx</other>
                </item1>

                <item1 id="0" method="change">
                    <otherchild>a</otherchild>
                </item1>
                <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                    <otherchild>a</otherchild>
                </item1>
            </section>
        </nodeA>

        <nodeA id="b">
            <section id="i">
                <item1 id="0" method="create">
                    <somechild>a</somechild>
                </item1>

                <item1 id="1" method="create">
                    <otherchild>a</otherchild>
                </item1>
            </section>

            <section id="i">
                <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                    <somechild>a</somechild>
                </item1>
                <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                    <somechild>bbb</somechild>
                </item1>
                <item1 id="3" method="create">
                    <other>xx</other>
                </item1>

                <item1 id="0" method="change">
                    <otherchild>a</otherchild>
                </item1>
                <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                    <otherchild>a</otherchild>
                </item1>
            </section>
        </nodeA>
</myroot>

产生了完全想要的结果，虽然要求定义严重并且实际上与想要的结果相矛盾 - 显然John在这方面有很大的改进空间：

<myroot>
   <nodeA id="a">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
         <item1 id="1" method="create">
            <otherchild>a</otherchild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this -->
         <somechild>bbb</somechild>
         </item1>
         <item1 id="3" method="create">
            <other>xx</other>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
   <nodeA id="b">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
         <item1 id="1" method="create">
            <otherchild>a</otherchild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this -->
          <somechild>bbb</somechild>
         </item1>
         <item1 id="3" method="create">
            <other>xx</other>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
</myroot>

Answer 2

将此文档作为输入文档....

<myroot>
    <nodeA id="a">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                <somechild>a</somechild>
            </item1>
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
            <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>

    <nodeA id="b">
        <section id="i">  
            <item1 id="0" method="create"> 
                <somechild>a</somechild>
            </item1>

            <item1 id="1" method="create">
                <otherchild>a</otherchild>
            </item1>
        </section>        

        <section id="i">
            <item1 id="0" method="create"> <!-- second consecutive create, we will remove this -->
                <somechild>a</somechild>
            </item1>
            <item1 id="0" method="create"> <!-- third consecutive create, BUT children have different value , so we don't remove this -->
                <somechild>bbb</somechild>
            </item1>
            <item1 id="3" method="create">
                <other>xx</other>    
            </item1>

            <item1 id="0" method="change"> 
                <otherchild>a</otherchild>
            </item1>
            <item1 id="0" method="change"> <!-- second consecutive create, we will remove this -->
                <otherchild>a</otherchild>
            </item1>
        </section>
    </nodeA>
</myroot>

..和这个样式表......

<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output indent="yes"/>
    <xsl:strip-space elements="*"/>

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

    <xsl:template match="*[*]
         [deep-equal(.,
           preceding::*[name()=current()/name()]
                       [@id = current()/@id]
                       [../../@id = current()/../../@id]
                       [1])]" />
</xsl:stylesheet>

...产生规定的所需输出......

<?xml version="1.0" encoding="UTF-8"?>
<myroot>
   <nodeA id="a">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
         <item1 id="1" method="create">
            <otherchild>a</otherchild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this --><somechild>bbb</somechild>
         </item1>
         <item1 id="3" method="create">
            <other>xx</other>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
   <nodeA id="b">
      <section id="i">
         <item1 id="0" method="create">
            <somechild>a</somechild>
         </item1>
         <item1 id="1" method="create">
            <otherchild>a</otherchild>
         </item1>
      </section>
      <section id="i">
         <item1 id="0" method="create"><!-- third consecutive create, BUT children have different value , so we don't remove this --><somechild>bbb</somechild>
         </item1>
         <item1 id="3" method="create">
            <other>xx</other>
         </item1>
         <item1 id="0" method="change">
            <otherchild>a</otherchild>
         </item1>
      </section>
   </nodeA>
</myroot>

注意，您可以使用这种稍微变化的样式表来帮助验证。它不是删除节点，而是通过插入节点来注释它们。查看它的输出有助于可视化正在发生的事情。

<xsl:stylesheet version="2.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output indent="yes"/>
    <xsl:strip-space elements="*"/>

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

    <xsl:template match="*[*]
         [deep-equal(.,
           preceding::*[name()=current()/name()]
                       [@id = current()/@id]
                       [../../@id = current()/../../@id]
                       [1])]" >
        <xsl:copy>
            <xsl:apply-templates select="@*" />
            <removed>
             <xsl:value-of select="'Parent of this node will be REMOVED.'" />
             <xsl:value-of select="../../@id" />
            </removed>
            <xsl:apply-templates select="node()" />
        </xsl:copy>
    </xsl:template>
    </xsl:stylesheet>