我有一个xml文档,如下所示:
<dict>
<word>
<sense>
<definition> This is the text of the definition.
<example>
<quote>This is the text of an example.</quote>
</example>
<source>
<place>This is the name of the place recorded</place>
</source>.
</definition>
</sense>
</word>
</dict>
我需要使用xQuery来转换它,使<example>
及其子项成为<definition>
的兄弟,而<source>
及其子项应成为<example>
的子项{1}}。换句话说,我需要这个作为输出:
<word>
<sense>
<definition> This is the text of the definition. </definition>
<example>
<quote>This is the text of an example.</quote>
<source>
<place>This is the name of the place recorded.</place>
</source>
</example>
</sense>
</word>
正如您所看到的,在<source>
关闭之前需要成为最后一个字符串的原始<place>
元素之后还存在一个句号问题。
我创建了一个xQuery文件并找出了如何从层次结构中删除元素,但是我在递归处理节点和在同一个函数中添加新元素时遇到了麻烦。
xquery version "3.0";
declare namespace saxon="http://saxon.sf.net/";
declare option saxon:output "indent=yes";
declare option saxon:output "saxon:indent-spaces=3";
declare function local:test($node as item()*) as item()* {
typeswitch($node)
case text() return normalize-space($node)
case element(word) return <word>{local:recurse($node)}</word>
case element(dict) return <dict>{local:recurse($node)}</dict>
case element(sense) return <sense>{local:recurse($node)}</sense>
case element(definition) return local:definition($node)
case element(example) return local:example($node)
case element(source) return local:source($node)
case element(place) return <place>{local:recurse($node)}</place>
default return local:recurse($node)
};
declare function local:definition($nodes as item()*) as item()*{
(: here I need to process children of definition - except <source> and its
children will become children of <example>; and <example> should be returned
as a next sibling of definition. THIS IS THE PART THAT I DON'T KNOW HOW TO DO :)
<definition>
{
for $node in $nodes/node()
return
local:test($node)
}
</definition>
};
declare function local:example($node as item()*) as item()* {
(: here i am removing <example> because I don't want it to be a child
of <definition> any more. THIS BIT WORKS AS IT SHOULD :)
if ($node/parent::definition) then ()
else <example>{$node/@*}{local:recurse($node)}</example>
};
declare function local:source($node as item()*) as item()* {
(: here i am removing <source> because I don't want it to be a child
of <definition> any more. :)
if ($node/parent::definition) then ()
else <example>{$node/@*}{local:recurse($node)}</example>
};
declare function local:recurse($nodes as item()*) as item()* {
for $node in $nodes/node()
return
local:test($node)
};
local:test(doc("file:test.xml"))
这不应该是一件非常困难的事情,但我对xQuery如何处理这类问题存在概念上的困难。我非常感谢你的帮助。
XSLT不是一个选项。
答案 0 :(得分:1)
我会选择 XQuery更新,这也得到Saxon的支持,并且会让这更容易。这会复制输入文件,但只需稍加修改,您也可以直接更改原始文档。
(: Copy the input file :)
copy $result := doc("file:test.xml")
modify (
for $definition in $result//definition
return (
(: Create new example element, and add it after the definition :)
insert node element example {
$definition/example/quote,
$definition/source
} after $definition,
(: Throw away the old elements :)
delete nodes $definition/(example, source)
)
)
return $result/dict/word
请注意,如果错误放置了点,这不会修复损坏的输入,但我也没有看到在您的代码中执行此操作的任何方法。
如果你更喜欢没有更新语句的版本,那么仍然不需要使用递归函数的复杂方法:
for $word in doc("file:test.xml")/dict/word
return element word {
for $sense in $word/sense
return element sense {
for $definition in $sense/definition
return (
element definition { $definition/text() },
element example { $definition/(example/quote, source) }
)
}
}
答案 1 :(得分:1)
仅仅为了完整性,这里有一个只有一个递归函数的递归XQuery 1.0 解决方案。我同意Jens的说法,给定的例子可以很容易地处理而不需要递归,但是如果真实的例子更大,并且你没有XQuery Update,你可以尝试这样的事情:
declare function local:recurse($node as item()*) as item()* {
typeswitch($node)
case text()
return normalize-space($node)
case element(definition)
return element {node-name($node)} {
$node/@*,
local:recurse($node/node() except $node/(example|source))
}
case element(sense)
return element {node-name($node)} {
$node/@*,
local:recurse($node/node()),
<example>{
$node/definition/example/@*,
$node/definition/example/node(),
$node/definition/source
}</example>
}
case element()
return element {node-name($node)} {
$node/@*,
local:recurse($node/node())
}
default return $node
};
let $xml :=
<dict>
<word>
<sense>
<definition> This is the text of the definition.
<example>
<quote>This is the text of an example.</quote>
</example>
<source>
<place>This is the name of the place recorded.</place>
</source>
</definition>
</sense>
</word>
</dict>
return local:recurse($xml)
HTH!