|
|
 next
|
  Subject: Cleaning up Word 2007 xml
Author: Paul Rayner
Date: 26 Jan 2009 10:20 AM
|
Hi,
I'm currently evaluating stylusstudio and marklogic.com's XML server with a view to using one or both within our company.
We need to clean up word XMl in several thousand documents, and I noticed a script at:
http://developer.marklogic.com/columns/smallchanges/2007-12-18.xqy
which makes a start towards this by combining 'runs'.
I am trying to make this script work within Stylus Studio, and have some problems I hope someone can help me with.
At the bottom of thispost I have pasted my modified version of the script. It currently produces the following error: XPTY0004, at line 103:24, which is the space after '$this' on the return statement of the local:map function.
I'm really just getting started with this, and hope to end up generating java code which can be run over a set of documents whenever needed. I'd appreciate any help anyone can give me.
Thanks,
Paul
code:
declare namespace w="http://schemas.openxmlformats.org/wordprocessingml/2006/main";
declare function local:ml-update-document-xml($doc as element(w:document)) as element(w:document)
{
local:dispatch($doc)
};
declare function local:passthru($x as node()) as node()
{
for $i in $x/node() return local:dispatch($i)
};
declare function local:dispatch ($x as node()) as node()
{
typeswitch ($x)
case element(w:p) return local:mergeruns($x)
default return (
element{fn:name($x)} {$x/@*,local:passthru($x)}
)
};
declare function local:mergeruns($p as element(w:p)) as element(w:p)
{
let $pPrvals := if(fn:exists($p/w:pPr)) then $p/w:pPr else ()
return element w:p{ $pPrvals, local:map($p/w:r[1]) }
};
declare function local:descend($r as element(w:r)?, $rToCheck as element(w:rPr)?) as element(w:r)*
{
if(fn:empty($r)) then ()
else if(fn:deep-equal($r/w:rPr,$rToCheck)) then
($r, local:descend($r/following-sibling::w:r[1], $rToCheck))
else ()
};
declare function local:map($r as element(w:r)?) as element(w:r)
{
if (fn:empty ($r)) then ()
else
let $rToCheck := $r/w:rPr
let $matches := local:descend($r/following-sibling::w:r[1], $rToCheck)
let $count := fn:count($matches)
let $this := if ($count) then
(element w:r{ $rToCheck,
element w:t { fn:string-join(($r/w:t, $matches/w:t),"") } })
else $r
return ($this, local:map( if($count) then ($r/following-sibling::w:r[1 + $count]) else $r/following-sibling::w:r[1]))
};
let $document :=
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
<w:body>
<w:p>
<w:pPr>
</w:pPr>
<w:r>
<w:rPr>
<w:i />
</w:rPr>
<w:t>Doctor Paul Pr</w:t>
</w:r>
<w:r>
<w:rPr>
<w:i />
</w:rPr>
<w:t>oteus, the man with the highe</w:t>
</w:r>
<w:r>
<w:rPr>
<w:i />
</w:rPr>
<w:t>st income in Ilium, drove his cheap and old Plymouth across the bridge to Homestead. </w:t>
</w:r>
</w:p>
</w:body>
</w:document>
return local:ml-update-document-xml($document)
|
|
|
|
top