我想从同一个父中删除连续重复节点，并且还有完全相同的孩子。
输入方案1：
<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 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>
</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 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>
</section>
</nodeA>
<nodeB 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 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>
</section>
</nodeB>
</myroot>
我的结果：
<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">
<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"/>
<section id="i"/>
</nodeA>
<nodeB id="b">
<section id="i"/>
<section id="i"/>
</nodeB>
</myroot>
预期输出：
<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">
<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">
<somechild>bbb</somechild>
</item1>
<item1 id="3" method="create">
<other>xx</other>
</item1>
<item1 id="0" method="change">
<otherchild>a</otherchild>
</item1>
</section>
</nodeA>
<nodeB 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">
<somechild>bbb</somechild>
</item1>
<item1 id="3" method="create">
<other>xx</other>
</item1>
<item1 id="0" method="change">
<otherchild>a</otherchild>
</item1>
</section>
</nodeB>
</myroot>
在上面的第一个场景中：只有第二个连续的create具有相同的子节点，而第三个连续的create方法具有不同的子节点，这就是为什么我们只删除第二个子节点。
第二种输入方案（更多变化）：
<myroot>
<nodeB id="a">
<cell id="i">
<item2 id="1" method="create">
<otherchild>a</otherchild>
</item2>
<item2 id="0" method="create">
<otherchild>a</otherchild>
</item2>
<item2 id="1" method="modify">
<otherchild>a</otherchild>
</item2>
</cell>
<cell id="i">
<item2 id="1" method="modify"> <!-- second consecutive modify, we remove this -->
<otherchild>a</otherchild>
</item2>
<item2 id="1" method="modify"> <!-- third consecutive modify, BUT different chldren, we do NOT remove this -->
<otherchild>a</otherchild>
<somechild>aa</somechild>
</item2>
<item2 id="1" method="delete" />
<item2 id="0" method="create">
<somechild>bbb</somechild>
</item2>
<item2 id="1" method="delete" /> <!-- second consecutive delete, we remove this -->
<item2 id="3" method="create">
<other>xx</other>
</item2>
<item2 id="1" method="delete" /> <!-- third consecutive delete, we remove this -->
</cell>
</nodeB>
</myroot>
输出：
<myroot>
<nodeB id="a">
<cell id="i">
<item2 id="1" method="create">
<otherchild>a</otherchild>
</item2>
<item2 id="0" method="create">
<otherchild>a</otherchild>
</item2>
<item2 id="1" method="modify">
<otherchild>a</otherchild>
</item2>
</cell>
<cell id="i">
<item2 id="1" method="modify">
<otherchild>a</otherchild>
<somechild>aa</somechild>
</item2>
<item2 id="1" method="delete" />
<item2 id="0" method="create">
<somechild>bbb</somechild>
</item2>
</cell>
</nodeB>
</myroot>
不执行此操作：
<myroot>
<node1 id="a">
<section id="i">
<item1 id="0" method="start">
<somechild>a</somechild>
</item1>
<item1 id="0" method="start"> <!-- this one is successive from the previous so we eliminate -->
<somechild>a</somechild>
</item1>
<item1 id="0" method="stop"/>
<item1 id="0" method="start"> <!-- this will be treated as new starting point -->
<somechild>a</somechild>
</item1>
</section>
<section id="i">
<item1 id="0" method="start"> <!-- this one is successive from the previous so we eliminate -->
<somechild>a</somechild>
</item1>
</section>
</node1>
</myroot>
output:
<myroot>
<node1 id="a">
<section id="i">
<item1 id="0" method="start">
<somechild>a</somechild>
</item1>
<item1 id="0" method="start"> <!-- this one is successive from the previous so we eliminate -->
<somechild>a</somechild>
</item1>
<item1 id="0" method="stop"/>
</section>
<section id="i"/>
</node1>
</myroot>
The correct output should be:
<myroot>
<node1 id="a">
<section id="i">
<item1 id="0" method="start">
<somechild>a</somechild>
</item1>
<item1 id="0" method="stop"/>
<item1 id="0" method="start"> <!-- this will be treated as new starting point -->
<somechild>a</somechild>
</item1>
</section>
<section id="i" />
</node1>
</myroot>
任何人都可以帮助我使用XSLT进行这种棘手的删除吗？ 非常感谢。
约翰
答案 0 :(得分：5)
这是一个XSLT 2.0示例样式表，应该可以完成这项工作，或者至少可以让您了解如何使用deep-equal提供帮助：
<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="2.0">
<xsl:strip-space elements="*"/>
<xsl:output indent="yes"/>
<xsl:template match="@* | node()">
<xsl:copy>
<xsl:apply-templates select="@* , node()"/>
</xsl:copy>
</xsl:template>
<xsl:template match="/*/*/*/*[some $el in (preceding-sibling::* , preceding::*) satisfies deep-equal(., $el)]"/>
</xsl:stylesheet>
[编辑]
根据新要求，我没有看到使用deep-equal解决该问题的方法，因此我编写了一个使用for-each-group和deep-equal的新样式表：
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="2.0">
<xsl:strip-space elements="*"/>
<xsl:output indent="yes"/>
<xsl:template match="@* | node()" name="identity">
<xsl:copy>
<xsl:apply-templates select="@* , node()"/>
</xsl:copy>
</xsl:template>
<xsl:template match="/*/*">
<xsl:copy>
<xsl:variable name="first-in-group" as="element()*">
<xsl:for-each-group select="*" group-by="concat(node-name(.), '|', @id)">
<xsl:for-each-group select="current-group()/*" group-by="concat(@id, '|', @method)">
<xsl:sequence
select="for $pos in 1 to count(current-group())
return current-group()[$pos]
[every $item
in subsequence(current-group(), 1, $pos - 1)
satisfies not(deep-equal($item, current-group()[$pos]))] "/>
</xsl:for-each-group>
</xsl:for-each-group>
</xsl:variable>
<xsl:apply-templates select="@*"/>
<xsl:apply-templates>
<xsl:with-param name="first-in-group" select="$first-in-group" tunnel="yes"/>
</xsl:apply-templates>
</xsl:copy>
</xsl:template>
<xsl:template match="/*/*/*/*">
<xsl:param name="first-in-group" tunnel="yes"/>
<xsl:if test="$first-in-group intersect .">
<xsl:call-template name="identity"/>
</xsl:if>
</xsl:template>
</xsl:stylesheet>
使用样式表Saxon 9.4，对样本应用时
<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 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>
</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 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>
</section>
</nodeA>
<nodeB 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 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>
</section>
</nodeB>
</myroot>
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 re
move 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 re
move 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>
<nodeB 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 re
move this --><somechild>bbb</somechild>
</item1>
<item1 id="3" method="create">
<other>xx</other>
</item1>
<item1 id="0" method="change">
<otherchild>a</otherchild>
</item1>
</section>
</nodeB>
</myroot>