992 lines
No EOL
123 KiB
HTML
992 lines
No EOL
123 KiB
HTML
<!DOCTYPE html><html xmlns="http:/www.w3.org/1999/xhtml"><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/><meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"/><meta http-equiv="Generator" content="xqdoca - https://github.com/quodatum/xqdoca"/><title>src - xqDocA - xqDocA</title><link rel="shortcut icon" type="image/x-icon" href="../../resources/xqdoc.png"/><link rel="stylesheet" type="text/css" href="../../resources/prism/1.29.0/prism.css"/><link rel="stylesheet" type="text/css" href="../../resources/page.css"/><link rel="stylesheet" type="text/css" href="../../resources/query.css"/><link rel="stylesheet" type="text/css" href="../../resources/base.css"/></head><body class="home" id="top"><div id="main" class="line-numbers"><div><h1><span class="badge badge-info">org.expkg_zone58.Pdfbox3</span>
|
||
<small>library module</small><div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></h1><nav id="toc"><h2><a href="../../index.html">src</a>
|
||
/ Module
|
||
</h2><h3><a id="contents"></a><span class="">org.expkg_zone58.Pdfbox3</span></h3><ol class="toc"><li><a href="#summary"><span class="secno">1 </span><span class="content">Summary</span></a></li><li><a href="#imports"><span class="secno">2 </span><span class="content">Imports</span></a></li><li><a href="#variables"><span class="secno">3 </span><span class="content">Variables</span></a><ol class="toc"><li><a href="#$pdfbox:property-map"><span class="secno">3.1</span><span class="content">$pdfbox:property-map</span><div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></a></li></ol></li><li><a href="#functions"><span class="secno">4 </span><span class="content">Functions</span></a><ol class="toc"><li><a href="#pdfbox:binary"><span class="secno">4.1</span><span class="content" title="Create binary representation of $pdf object as xs:base64Binary">binary<div style="float:right"></div></span></a></li><li><a href="#pdfbox:bookmark"><span class="secno">4.2</span><span class="content" title="Return bookmark info for $bookmark">bookmark<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:bookmark-xml"><span class="secno">4.3</span><span class="content" title="Convert outline map to XML">bookmark-xml<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:close"><span class="secno">4.4</span><span class="content" title="Release any resources related to $pdf">close<div style="float:right"></div></span></a></li><li><a href="#pdfbox:do-until"><span class="secno">4.5</span><span class="content" title="fn:do-until shim for BaseX 9+10 if fn:do-until not found use hof:until, note: $pos always zero">do-until<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:extract-range"><span class="secno">4.6</span><span class="content" title="Return new PDF doc with pages from $start to $end as xs:base64Binary, (1 based)">extract-range<div style="float:right"></div></span></a></li><li><a href="#pdfbox:find-page"><span class="secno">4.7</span><span class="content" title="pageIndex of $page in $pdf">find-page<div style="float:right"></div></span></a></li><li><a href="#pdfbox:gregToISO"><span class="secno">4.8</span><span class="content" title="Convert date">gregToISO<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:label-as-map"><span class="secno">4.9</span><span class="content" title="express label/page-range for $page as map">label-as-map<div style="float:right"></div></span></a></li><li><a href="#pdfbox:label-as-string"><span class="secno">4.10</span><span class="content" title="label for $page formated as string">label-as-string<div style="float:right"></div></span></a></li><li><a href="#pdfbox:labels-as-map"><span class="secno">4.11</span><span class="content" title="sequence of maps for each label in">labels-as-map<div style="float:right"></div></span></a></li><li><a href="#pdfbox:labels-as-strings"><span class="secno">4.12</span><span class="content" title="sequence of label ranges defined in PDF as formatted strings">labels-as-strings<div style="float:right"></div></span></a></li><li><a href="#pdfbox:labels-by-page"><span class="secno">4.13</span><span class="content" title="pageLabel for every page from derived from page-ranges The returned sequence will contain at MOST as much entries as the document has pages.">labels-by-page<div style="float:right"></div></span></a></li><li><a href="#pdfbox:metadata"><span class="secno">4.14</span><span class="content" title="XMP metadata as "RDF" document">metadata<div style="float:right"></div></span></a></li><li><a href="#pdfbox:number-of-bookmarks"><span class="secno">4.15</span><span class="content" title="number of outline items">number-of-bookmarks<div style="float:right"></div></span></a></li><li><a href="#pdfbox:number-of-labels"><span class="secno">4.16</span><span class="content" title="The number of labels defined in PDF">number-of-labels<div style="float:right"></div></span></a></li><li><a href="#pdfbox:number-of-pages"><span class="secno">4.17</span><span class="content" title="Number of pages in PDF">number-of-pages<div style="float:right"></div></span></a></li><li><a href="#pdfbox:open"><span class="secno">4.18</span><span class="content" title="open pdf using fetch:binary, returns pdf object">open<div style="float:right"></div></span></a></li><li><a href="#pdfbox:outline"><span class="secno">4.19</span><span class="content" title="outline for $pdf as map()*">outline<div style="float:right"></div></span></a></li><li><a href="#pdfbox:outline-xml"><span class="secno">4.20</span><span class="content" title="PDF outline in xml format">outline-xml<div style="float:right"></div></span></a></li><li><a href="#pdfbox:outline_"><span class="secno">4.21</span><span class="content" title="BaseX bug 10.7? error if inlined in outline">outline_<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:page-labels"><span class="secno">4.22</span><span class="content" title="get pagelabels exist">page-labels<div style="float:right"></div></span></a></li><li><a href="#pdfbox:page-media-box"><span class="secno">4.23</span><span class="content" title="Return size of $pageNo (zero based)">page-media-box<div style="float:right"></div></span></a></li><li><a href="#pdfbox:page-render"><span class="secno">4.24</span><span class="content" title="Pdf page as image (zero is cover) options.format="bmp jpg png gif" etc, options.scale= 1 is 72 dpi??">page-render<div style="float:right"></div></span></a></li><li><a href="#pdfbox:page-text"><span class="secno">4.25</span><span class="content" title="return text on $pageNo">page-text<div style="float:right"></div></span></a></li><li><a href="#pdfbox:pdf-save"><span class="secno">4.26</span><span class="content" title="Save pdf $pdf to filesystem at $savepath , returns $savepath">pdf-save<div style="float:right"></div></span></a></li><li><a href="#pdfbox:property"><span class="secno">4.27</span><span class="content" title="return value of $property for $pdf">property<div style="float:right"></div></span></a></li><li><a href="#pdfbox:property-names"><span class="secno">4.28</span><span class="content" title="known property names sorted">property-names<div style="float:right"></div></span></a></li><li><a href="#pdfbox:read-stream"><span class="secno">4.29</span><span class="content" title="read next block from XMP stream">read-stream<div style="float:right"><span class="badge badge-dark" title="Private">P</span></div></span></a></li><li><a href="#pdfbox:report"><span class="secno">4.30</span><span class="content" title="summary CSV style info for all properties for $pdfpaths">report<div style="float:right"></div></span></a></li><li><a href="#pdfbox:report-save"><span class="secno">4.31</span><span class="content" title="convenience function to save report() data to file">report-save<div style="float:right"></div></span></a></li><li><a href="#pdfbox:specification"><span class="secno">4.32</span><span class="content" title="The version of the PDF specification used by $pdf e.g "1.4" returned as string to avoid float rounding issues">specification<div style="float:right"></div></span></a></li><li><a href="#pdfbox:version"><span class="secno">4.33</span><span class="content" title="Version of Apache Pdfbox in use e.g. "3.0.4"">version<div style="float:right"></div></span></a></li><li><a href="#pdfbox:with-pdf"><span class="secno">4.34</span><span class="content" title=""With-document" pattern: open pdf,apply $fn function, close pdf creates a local pdfobject and ensures it is closed after use e.g pdfbox:with-pdf("path...",pdfbox:page-text(?,5))">with-pdf<div style="float:right"></div></span></a></li></ol></li><li><a href="#namespaces"><span class="secno">5 </span><span class="content">Namespaces</span></a></li><li><a href="#restxq"><span class="secno">6 </span><span class="content">RestXQ</span></a></li><li><a href="#source"><span class="secno">7 </span><span class="content">Source</span></a></li></ol></nav><section id="summary"><h2>Summary</h2><div>
|
||

|
||
A BaseX 10.7+ interface to pdfbox3 https://pdfbox.apache.org/ ,
|
||
requires pdfbox jars on classpath, in lib/custom or xar
|
||
refer to the same concept. Also label and (page)range are used interchangably
|
||
</div><dl><dt title="1">See also</dt><dd><ul><li><span><a href="https://pdfbox.apache.org/download.cgi">https://pdfbox.apache.org/download.cgi</a></span></li></ul></dd></dl><dl><dt title="1">Authors</dt><dd><ul><li><span>Andy Bunce 2025</span></li></ul></dd></dl><dl><dt title="3">Custom</dt><dd><ul><li><span><span class="badge badge-pill badge-light">@note</span>:
|
||
<span>following the java source the terms outline and bookmark</span></span></li><li><span><span class="badge badge-pill badge-light">@note</span>:
|
||
<span>tested with pdfbox-app-3.0.5.jar</span></span></li><li><span>Javadoc: <a href="https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.5/" target="_blank"><custom tag="javadoc">https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.5/</custom></a></span></li></ul></dd></dl><details><summary>Related documents</summary><table class="data"><thead><th>View</th><th>Description</th><th>Format</th></thead><tbody><tr><td><a href="xqdoc.xml" title="xqDoc xml file from the source module " class="badge badge-pill badge-light" style="margin-left:1em" target="_blank">xqdoc</a></td><td>xqDoc xml file from the source module</td><td>xml</td></tr><tr><td><a href="xqparse.xml" title="xqparse xml file from the source module " class="badge badge-pill badge-light" style="margin-left:1em" target="_blank">xqparse</a></td><td>xqparse xml file from the source module</td><td>xml</td></tr></tbody></table></details></section><section id="imports"><h2>Imports</h2><p>
|
||
This module is imported by
|
||
<span class="badge badge-info">0</span> modules. It imports
|
||
<span class="badge badge-info">0</span> modules.
|
||
</p></section><section id="variables"><h2>Variables</h2><div class="div3"><h3><a id="$pdfbox:property-map"></a><a id="{org.expkg_zone58.Pdfbox3}$property-map"></a><a href="#$pdfbox:property-map">3.1 </a>$pdfbox:property-map</h3><dl><dt class="label">Summary</dt><dd>
|
||
property access map
|
||
keys are property names,
|
||
values are sequences of functions to get property from $pdf object
|
||
</dd><dt class="label">Type</dt><dd></dd></dl><details><summary>References 15 functions from 3 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getAuthor#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getCreationDate#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getCreator#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getKeywords#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getModificationDate#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getProducer#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getSubject#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocumentInformation}getTitle#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentInformation#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}gregToISO#1" title="Pdfbox3.xqm">pdfbox:gregToISO#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}labels-as-strings#1" title="Pdfbox3.xqm">pdfbox:labels-as-strings#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-bookmarks#1" title="Pdfbox3.xqm">pdfbox:number-of-bookmarks#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-labels#1" title="Pdfbox3.xqm">pdfbox:number-of-labels#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-pages#1" title="Pdfbox3.xqm">pdfbox:number-of-pages#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}specification#1" title="Pdfbox3.xqm">pdfbox:specification#1</a></span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details open="open"><summary>Source ( 36 lines)</summary><pre><code class="language-xquery" data-prismjs-copy="Copy to clipboard">variable $pdfbox:property-map:=map{
|
||
"#pages": pdfbox:number-of-pages#1,
|
||

|
||
"#bookmarks": pdfbox:number-of-bookmarks#1,
|
||

|
||
"#labels": pdfbox:number-of-labels#1,
|
||

|
||
"specification":pdfbox:specification#1,
|
||

|
||
"title": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getTitle#1) ,
|
||

|
||
"author": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getAuthor#1 ),
|
||

|
||
"creator": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getCreator#1),
|
||

|
||
"producer": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getProducer#1),
|
||

|
||
"subject": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getSubject#1),
|
||

|
||
"keywords": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getKeywords#1),
|
||

|
||
"creationDate": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getCreationDate#1,
|
||
pdfbox:gregToISO#1),
|
||

|
||
"modificationDate": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getModificationDate#1,
|
||
pdfbox:gregToISO#1),
|
||
"labels": pdfbox:labels-as-strings#1 
|
||
}</code></pre></details></div></section><section id="functions"><h2>Functions</h2><div class="div3"><h3><a id="pdfbox:binary"></a><a id="{org.expkg_zone58.Pdfbox3}binary#1"></a><a href="#pdfbox:binary">4.1 </a>pdfbox:binary</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}binary#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Create binary representation of $pdf object as xs:base64Binary</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:binary</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:base64Binary</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:base64Binary</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}extract-range#3" title="Pdfbox3.xqm">pdfbox:extract-range#3</a></span></li></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:java.io.ByteArrayOutputStream}new#0</span></li><li><span class="badge badge-warning" title="Externally defined">{java:java.io.ByteArrayOutputStream}toByteArray#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}save#2</span></li></ul></details><details><summary>Source ( 7 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:binary($pdf as item())
|
||
as xs:base64Binary{
|
||
let $bytes:=Q{java:java.io.ByteArrayOutputStream}new()
|
||
let $_:=PDDocument:save($pdf, $bytes)
|
||
return Q{java:java.io.ByteArrayOutputStream}toByteArray($bytes)
|
||
=>convert:integers-to-base64()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:bookmark"></a><a id="{org.expkg_zone58.Pdfbox3}bookmark#2"></a><a href="#pdfbox:bookmark">4.2 </a>pdfbox:bookmark</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}bookmark#2">#2</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
Return bookmark info for $bookmark
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:bookmark</code>
|
||
(
|
||
<code class="arg">$bookmark</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">map(*)</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>bookmark<code class="as"> as </code><code class="return-type">item()</code></li><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*)</code> map{index:..,title:..,hasChildren:..}</li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline_#2" title="Pdfbox3.xqm">pdfbox:outline_#2</a></span></li></ul></details><details><summary>References 3 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}findDestinationPage#2</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}getTitle#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}hasChildren#1</span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 10 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:bookmark($bookmark as item(),$pdf as item())
|
||
as map(*)
|
||
{
|
||
map{ 
|
||
"index": PDOutlineItem:findDestinationPage($bookmark,$pdf)=>pdfbox:find-page($pdf),
|
||
"title": (# db:checkstrings #) {PDOutlineItem:getTitle($bookmark)}
|
||
(:=>translate("<22>",""), :),
|
||
"hasChildren": PDOutlineItem:hasChildren($bookmark)
|
||
}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:bookmark-xml"></a><a id="{org.expkg_zone58.Pdfbox3}bookmark-xml#1"></a><a href="#pdfbox:bookmark-xml">4.3 </a>pdfbox:bookmark-xml</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}bookmark-xml#1">#1</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
Convert outline map to XML</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:bookmark-xml</code>
|
||
(
|
||
<code class="arg">$outline</code><code class="as"> as </code><code class="type">map(*)*</code> )<code class="as"> as </code><code class="type">element(bookmark)*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>outline<code class="as"> as </code><code class="return-type">map(*)*</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">element(bookmark) *</code></li></ul></dd><details><summary>Referenced by 2 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline-xml#1" title="Pdfbox3.xqm">pdfbox:outline-xml#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}bookmark-xml#1" title="Pdfbox3.xqm">pdfbox:bookmark-xml#1</a></span></li></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}bookmark-xml#1" title="Pdfbox3.xqm">pdfbox:bookmark-xml#1</a></span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 8 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:bookmark-xml($outline as map(*)*)
|
||
as element(bookmark)*
|
||
{
|
||
$outline!
|
||
<bookmark title="{?title}" index="{?index}">
|
||
{?children!pdfbox:bookmark-xml(.)}
|
||
</bookmark>
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:close"></a><a id="{org.expkg_zone58.Pdfbox3}close#1"></a><a href="#pdfbox:close">4.4 </a>pdfbox:close</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}close#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Release any resources related to $pdf</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:close</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">empty-sequence</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">empty-sequence</code></li></ul></dd><details><summary>Referenced by 3 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}with-pdf#2" title="Pdfbox3.xqm">pdfbox:with-pdf#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#2" title="Pdfbox3.xqm">pdfbox:report#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}extract-range#3" title="Pdfbox3.xqm">pdfbox:extract-range#3</a></span></li></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}close#1</span></li></ul></details><details><summary>Source ( 6 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:close($pdf as item())
|
||
as empty-sequence(){
|
||
(# db:wrapjava void #) {
|
||
PDDocument:close($pdf)
|
||
}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:do-until"></a><a id="{org.expkg_zone58.Pdfbox3}do-until#3"></a><a href="#pdfbox:do-until">4.5 </a>pdfbox:do-until</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}do-until#3">#3</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
fn:do-until shim for BaseX 9+10
|
||
if fn:do-until not found use hof:until, note: $pos always zero
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:do-until</code>
|
||
(
|
||
<code class="arg">$input</code><code class="as"> as </code><code class="type">item()*</code>, <code class="arg">$action</code><code class="as"> as </code><code class="type">function(item()*, xs:integer) as item()*</code>, <code class="arg">$predicate</code><code class="as"> as </code><code class="type">function(item()*, xs:integer) as xs:boolean?</code> )<code class="as"> as </code><code class="type">item()*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>input<code class="as"> as </code><code class="return-type">item()*</code></li><li>action<code class="as"> as </code><code class="return-type">function(item()*, xs:integer) as item()*</code></li><li>predicate<code class="as"> as </code><code class="return-type">function(item()*, xs:integer) as xs:boolean?</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">item() *</code></li></ul></dd><details><summary>Referenced by 2 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}metadata#1" title="Pdfbox3.xqm">pdfbox:metadata#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline_#2" title="Pdfbox3.xqm">pdfbox:outline_#2</a></span></li></ul></details><details><summary>References 5 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2001/XMLSchema}QName#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}QName#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}error#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}function-lookup#2</span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 15 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:do-until(
|
||
$input as item()*, 
|
||
$action as function(item()*, xs:integer) as item()*, 
|
||
$predicate as function(item()*, xs:integer) as xs:boolean? 
|
||
) as item()*
|
||
{
|
||
let $fn:=function-lookup(QName('http://www.w3.org/2005/xpath-functions','do-until'), 3)
|
||
return if(exists($fn))
|
||
then $fn($input,$action,$predicate)
|
||
else let $hof:=function-lookup(QName('http://basex.org/modules/hof','until'), 3)
|
||
return if(exists($hof))
|
||
then $hof($predicate(?,0),$action(?,0),$input)
|
||
else error(xs:QName('pdfbox:do-until'),"No implementation do-until found")
|
||

|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:extract-range"></a><a id="{org.expkg_zone58.Pdfbox3}extract-range#3"></a><a href="#pdfbox:extract-range">4.6 </a>pdfbox:extract-range</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}extract-range#3">#3</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Return new PDF doc with pages from $start to $end as xs:base64Binary, (1 based)
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:extract-range</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$start</code><code class="as"> as </code><code class="type">xs:integer</code>, <code class="arg">$end</code><code class="as"> as </code><code class="type">xs:integer</code> )<code class="as"> as </code><code class="type">xs:base64Binary</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>start<code class="as"> as </code><code class="return-type">xs:integer</code> first page to include</li><li>end<code class="as"> as </code><code class="return-type">xs:integer</code> last page to include</li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:base64Binary</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.multipdf.PageExtractor}new#3</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}binary#1" title="Pdfbox3.xqm">pdfbox:binary#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}close#1" title="Pdfbox3.xqm">pdfbox:close#1</a></span></li></ul></details><details><summary>Source ( 7 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:extract-range($pdf as item(), 
|
||
$start as xs:integer,$end as xs:integer)
|
||
as xs:base64Binary
|
||
{
|
||
let $a:=PageExtractor:new($pdf, $start, $end) =>PageExtractor:extract()
|
||
return (pdfbox:binary($a),pdfbox:close($a)) 
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:find-page"></a><a id="{org.expkg_zone58.Pdfbox3}find-page#2"></a><a href="#pdfbox:find-page">4.7 </a>pdfbox:find-page</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}find-page#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
pageIndex of $page in $pdf</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:find-page</code>
|
||
(
|
||
<code class="arg">$page</code><code class="as"> as </code><code class="type">item()?</code>, <code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">item()?</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>page<code class="as"> as </code><code class="return-type">item()?</code></li><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">item() ?</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li></ul></details><details><summary>Source ( 10 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:find-page(
|
||
$page as item()? (: as java:org.apache.pdfbox.pdmodel.PDPage :),
|
||
$pdf as item())
|
||
as item()?
|
||
{
|
||
if(exists($page))
|
||
then PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPages()
|
||
=>PDPageTree:indexOf($page)
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:gregToISO"></a><a id="{org.expkg_zone58.Pdfbox3}gregToISO#1"></a><a href="#pdfbox:gregToISO">4.8 </a>pdfbox:gregToISO</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}gregToISO#1">#1</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
Convert date</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:gregToISO</code>
|
||
(
|
||
<code class="arg">$item</code><code class="as"> as </code><code class="type">item()?</code> )<code class="as"> as </code><code class="type">xs:string?</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>item<code class="as"> as </code><code class="return-type">item()?</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string ?</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:java.util.GregorianCalendar}toZonedDateTime#1</span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 6 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:gregToISO($item as item()?)
|
||
as xs:string?{
|
||
if(exists($item))
|
||
then Q{java:java.util.GregorianCalendar}toZonedDateTime($item)=>string()
|
||
else ()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:label-as-map"></a><a id="{org.expkg_zone58.Pdfbox3}label-as-map#2"></a><a href="#pdfbox:label-as-map">4.9 </a>pdfbox:label-as-map</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}label-as-map#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
express label/page-range for $page as map</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:label-as-map</code>
|
||
(
|
||
<code class="arg">$pagelabels</code>, <code class="arg">$page</code><code class="as"> as </code><code class="type">xs:integer</code> )<code class="as"> as </code><code class="type">map(*)</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pagelabels<code class="as"> as </code><code class="return-type"></code></li><li>page<code class="as"> as </code><code class="return-type">xs:integer</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*)</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}labels-as-map#1" title="Pdfbox3.xqm">pdfbox:labels-as-map#1</a></span></li></ul></details><details><summary>References 5 functions from 3 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}empty#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getPrefix#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getStart#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getStyle#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabels}getPageLabelRange#2</span></li></ul></details><details><summary>Source ( 13 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:label-as-map($pagelabels,$page as xs:integer)
|
||
as map(*)
|
||
{
|
||
let $label:=PDPageLabels:getPageLabelRange($pagelabels,$page)
|
||
return if(empty($label))
|
||
then ()
|
||
else map{
|
||
"index": $page,
|
||
"prefix": PDPageLabelRange:getPrefix($label),
|
||
"start": PDPageLabelRange:getStart($label),
|
||
"style": PDPageLabelRange:getStyle($label)
|
||
}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:label-as-string"></a><a id="{org.expkg_zone58.Pdfbox3}label-as-string#2"></a><a href="#pdfbox:label-as-string">4.10 </a>pdfbox:label-as-string</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}label-as-string#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
label for $page formated as string</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:label-as-string</code>
|
||
(
|
||
<code class="arg">$pagelabels</code>, <code class="arg">$page</code><code class="as"> as </code><code class="type">xs:integer</code> )<code class="as"> as </code><code class="type">xs:string?</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pagelabels<code class="as"> as </code><code class="return-type"></code></li><li>page<code class="as"> as </code><code class="return-type">xs:integer</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string ?</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}labels-as-strings#1" title="Pdfbox3.xqm">pdfbox:labels-as-strings#1</a></span></li></ul></details><details><summary>References 7 functions from 3 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}empty#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}string-join#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getPrefix#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getStart#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange}getStyle#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabels}getPageLabelRange#2</span></li></ul></details><details><summary>Source ( 15 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:label-as-string($pagelabels,$page as xs:integer)
|
||
as xs:string?{
|
||
let $label:=PDPageLabels:getPageLabelRange($pagelabels,$page)
|
||
return if(empty($label))
|
||
then ()
|
||
else
|
||
let $start:= PDPageLabelRange:getStart($label)
|
||
let $style := PDPageLabelRange:getStyle($label)
|
||
let $prefix:= PDPageLabelRange:getPrefix($label) 
|
||
return string-join(($page, 
|
||
if(empty($style)) then "-" else $style,
|
||
if(($start eq 1)) then "" else $start,
|
||
if(exists($prefix)) then '*' || $prefix (:TODO double " :)
|
||
))
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:labels-as-map"></a><a id="{org.expkg_zone58.Pdfbox3}labels-as-map#1"></a><a href="#pdfbox:labels-as-map">4.11 </a>pdfbox:labels-as-map</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}labels-as-map#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
sequence of maps for each label in</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:labels-as-map</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">map(*)*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*) *</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}label-as-map#2" title="Pdfbox3.xqm">pdfbox:label-as-map#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-pages#1" title="Pdfbox3.xqm">pdfbox:number-of-pages#1</a></span></li></ul></details><details><summary>Source ( 8 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:labels-as-map($pdf as item())
|
||
as map(*)*{
|
||
let $pagelabels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return $pagelabels
|
||
!(0 to pdfbox:number-of-pages($pdf)-1)
|
||
!pdfbox:label-as-map($pagelabels,.)
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:labels-as-strings"></a><a id="{org.expkg_zone58.Pdfbox3}labels-as-strings#1"></a><a href="#pdfbox:labels-as-strings">4.12 </a>pdfbox:labels-as-strings</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}labels-as-strings#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
sequence of label ranges defined in PDF as formatted strings</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:labels-as-strings</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}label-as-string#2" title="Pdfbox3.xqm">pdfbox:label-as-string#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-pages#1" title="Pdfbox3.xqm">pdfbox:number-of-pages#1</a></span></li></ul></details><details><summary>Source ( 9 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:labels-as-strings($pdf as item())
|
||
as xs:string{
|
||
let $pagelabels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return $pagelabels
|
||
!(0 to pdfbox:number-of-pages($pdf)-1)
|
||
!pdfbox:label-as-string($pagelabels,.)=>string-join(",")
|
||

|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:labels-by-page"></a><a id="{org.expkg_zone58.Pdfbox3}labels-by-page#1"></a><a href="#pdfbox:labels-by-page">4.13 </a>pdfbox:labels-by-page</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}labels-by-page#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
pageLabel for every page from derived from page-ranges
|
||
The returned sequence will contain at MOST as much entries as the document has pages.
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:labels-by-page</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:string*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string *</code></li></ul></dd><dl><dt title="2">Tags</dt><dd><ul><li><span><a href="https://www.w3.org/TR/WCAG20-TECHS/PDF17.html#PDF17-examples">https://www.w3.org/TR/WCAG20-TECHS/PDF17.html#PDF17-examples</a></span></li><li><span><a href="https://codereview.stackexchange.com/questions/286078/java-code-showing-page-labels-from-pdf-files">https://codereview.stackexchange.com/questions/286078/java-code-showing-page-labels-from-pdf-files</a></span></li></ul></dd></dl><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li></ul></details><details><summary>Source ( 7 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:labels-by-page($pdf as item())
|
||
as xs:string*
|
||
{
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
=>PDPageLabels:getLabelsByPageIndices()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:metadata"></a><a id="{org.expkg_zone58.Pdfbox3}metadata#1"></a><a href="#pdfbox:metadata">4.14 </a>pdfbox:metadata</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}metadata#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
XMP metadata as "RDF" document
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:metadata</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">document-node(element(*))?</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">document-node(element(*)) ?</code></li></ul></dd><dl><dt title="1">Tags</dt><dd><ul><li><span><span class="badge badge-pill badge-light">@note</span>:
|
||
<span>usually rdf:RDF root, but sometimes x:xmpmeta</span></span></li></ul></dd></dl><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 5 functions from 4 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDMetadata}exportXMPMetadata#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}do-until#3" title="Pdfbox3.xqm">pdfbox:do-until#3</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}read-stream#2" title="Pdfbox3.xqm">pdfbox:read-stream#2</a></span></li></ul></details><details><summary>Source ( 17 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:metadata($pdf as item())
|
||
as document-node(element(*))?
|
||
{
|
||
let $m:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getMetadata()
|
||
return if(exists($m))
|
||
then 
|
||
let $is:=PDMetadata:exportXMPMetadata($m)
|
||
return pdfbox:do-until(
|
||
map{"n":0,"data":""},
|
||

|
||
function($input,$pos ) { pdfbox:read-stream($is,$input?data)},
|
||

|
||
function($output,$pos) { $output?n eq -1 } 
|
||
)?data=>parse-xml()
|
||
else ()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:number-of-bookmarks"></a><a id="{org.expkg_zone58.Pdfbox3}number-of-bookmarks#1"></a><a href="#pdfbox:number-of-bookmarks">4.15 </a>pdfbox:number-of-bookmarks</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}number-of-bookmarks#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
number of outline items</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:number-of-bookmarks</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:integer</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:integer</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}count#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline-xml#1" title="Pdfbox3.xqm">pdfbox:outline-xml#1</a></span></li></ul></details><details><summary>Source ( 5 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:number-of-bookmarks($pdf as item())
|
||
as xs:integer{
|
||
let $xml:=pdfbox:outline-xml($pdf)
|
||
return count($xml//bookmark)
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:number-of-labels"></a><a id="{org.expkg_zone58.Pdfbox3}number-of-labels#1"></a><a href="#pdfbox:number-of-labels">4.16 </a>pdfbox:number-of-labels</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}number-of-labels#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
The number of labels defined in PDF</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:number-of-labels</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:integer</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:integer</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 3 functions from 3 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.common.PDPageLabels}getPageRangeCount#1</span></li></ul></details><details><summary>Source ( 9 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:number-of-labels($pdf as item())
|
||
as xs:integer
|
||
{
|
||
let $labels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return if(exists($labels)) 
|
||
then PDPageLabels:getPageRangeCount($labels)
|
||
else 0
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:number-of-pages"></a><a id="{org.expkg_zone58.Pdfbox3}number-of-pages#1"></a><a href="#pdfbox:number-of-pages">4.17 </a>pdfbox:number-of-pages</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}number-of-pages#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Number of pages in PDF</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:number-of-pages</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:integer</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:integer</code></li></ul></dd><details><summary>Referenced by 2 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}labels-as-strings#1" title="Pdfbox3.xqm">pdfbox:labels-as-strings#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}labels-as-map#1" title="Pdfbox3.xqm">pdfbox:labels-as-map#1</a></span></li></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getNumberOfPages#1</span></li></ul></details><details><summary>Source ( 4 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:number-of-pages($pdf as item())
|
||
as xs:integer{
|
||
PDDocument:getNumberOfPages($pdf)
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:open"></a><a id="{org.expkg_zone58.Pdfbox3}open#1"></a><a id="{org.expkg_zone58.Pdfbox3}open#2"></a><a href="#pdfbox:open">4.18 </a>pdfbox:open</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}open#1">#1</a><span style="margin-left:1em"></span></span><span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}open#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
open pdf using fetch:binary, returns pdf object</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:open</code>
|
||
(
|
||
<code class="arg">$pdfsrc</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">item()</code></div><div class="proto"><code class="function">pdfbox:open</code>
|
||
(
|
||
<code class="arg">$pdfsrc</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$opts</code><code class="as"> as </code><code class="type">map(*)</code> )<code class="as"> as </code><code class="type">item()</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdfsrc<code class="as"> as </code><code class="return-type">item()</code> a fetchable url or filepath, or xs:base64Binary item</li><li>opts<code class="as"> as </code><code class="return-type">map(*)</code> options options include map {"password":}</li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">item()</code></li></ul></dd><dl><dt title="1">Tags</dt><dd><ul><li><span><span class="badge badge-pill badge-light">@note</span>:
|
||
<span>fetch:binary for https will use a lot of memory here</span></span></li></ul></dd></dl><details><summary>Referenced by 3 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}with-pdf#2" title="Pdfbox3.xqm">pdfbox:with-pdf#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}open#1" title="Pdfbox3.xqm">pdfbox:open#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#2" title="Pdfbox3.xqm">pdfbox:report#2</a></span></li></ul></details><details><summary>References 8 functions from 6 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://basex.org/modules/fetch}binary#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2001/XMLSchema}QName#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}error#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}starts-with#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}string#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.Loader}loadPDF#2</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.io.RandomAccessReadBufferedFile}new#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}open#2" title="Pdfbox3.xqm">pdfbox:open#2</a></span></li></ul></details><details><summary>Source ( 21 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:open($pdfsrc as item())
|
||
as item(){
|
||
pdfbox:open($pdfsrc, map{})
|
||
}</code></pre><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:open($pdfsrc as item(), $opts as map(*))
|
||
as item(){
|
||
try{
|
||

|
||
if($pdfsrc instance of xs:base64Binary)
|
||
then Loader:loadPDF( $pdfsrc,string($opts?password))
|
||
else if(starts-with($pdfsrc,"http"))
|
||
then Loader:loadPDF( fetch:binary($pdfsrc),string($opts?password))
|
||
else Loader:loadPDF(RandomAccessReadBufferedFile:new($pdfsrc),string($opts?password))
|
||

|
||
} catch *{
|
||
let $loc:=if($pdfsrc instance of xs:base64Binary)
|
||
then "xs:base64Binary"
|
||
else $pdfsrc
|
||
return error(xs:QName("pdfbox:open"),"Failed PDF load " || $loc || " " || $err:description)
|
||
}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:outline"></a><a id="{org.expkg_zone58.Pdfbox3}outline#1"></a><a id="{org.expkg_zone58.Pdfbox3}outline#2"></a><a href="#pdfbox:outline">4.19 </a>pdfbox:outline</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}outline#1">#1</a><span style="margin-left:1em"></span></span><span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}outline#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
outline for $pdf as map()*</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:outline</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">map(*)*</code></div><div class="proto"><code class="function">pdfbox:outline</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$outlineItem</code><code class="as"> as </code><code class="type">item()?</code> )<code class="as"> as </code><code class="type">map(*)*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>outlineItem<code class="as"> as </code><code class="return-type">item()?</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*) *</code></li></ul></dd><details><summary>Referenced by 3 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline#1" title="Pdfbox3.xqm">pdfbox:outline#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline_#2" title="Pdfbox3.xqm">pdfbox:outline_#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline-xml#1" title="Pdfbox3.xqm">pdfbox:outline-xml#1</a></span></li></ul></details><details><summary>References 6 functions from 5 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions/map}get#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}getFirstChild#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline#2" title="Pdfbox3.xqm">pdfbox:outline#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline_#2" title="Pdfbox3.xqm">pdfbox:outline_#2</a></span></li></ul></details><details><summary>Source ( 16 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:outline($pdf as item())
|
||
as map(*)*{
|
||
(# db:wrapjava some #) {
|
||
let $outline:=
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getDocumentOutline()
|
||

|
||
return if(exists($outline))
|
||
then pdfbox:outline($pdf,PDOutlineItem:getFirstChild($outline)) 
|
||
}
|
||
}</code></pre><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:outline($pdf as item(),$outlineItem as item()?)
|
||
as map(*)*{
|
||
let $find as map(*):=pdfbox:outline_($pdf ,$outlineItem)
|
||
return map:get($find,"list")
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:outline-xml"></a><a id="{org.expkg_zone58.Pdfbox3}outline-xml#1"></a><a href="#pdfbox:outline-xml">4.20 </a>pdfbox:outline-xml</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}outline-xml#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
PDF outline in xml format</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:outline-xml</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">element(outline)?</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">element(outline) ?</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}number-of-bookmarks#1" title="Pdfbox3.xqm">pdfbox:number-of-bookmarks#1</a></span></li></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}bookmark-xml#1" title="Pdfbox3.xqm">pdfbox:bookmark-xml#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline#1" title="Pdfbox3.xqm">pdfbox:outline#1</a></span></li></ul></details><details><summary>Source ( 7 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:outline-xml($pdf as item())
|
||
as element(outline)?{
|
||
let $outline:=pdfbox:outline($pdf)
|
||
return if(exists($outline))
|
||
then <outline>{$outline!pdfbox:bookmark-xml(.)}</outline>
|
||
else ()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:outline_"></a><a id="{org.expkg_zone58.Pdfbox3}outline_#2"></a><a href="#pdfbox:outline_">4.21 </a>pdfbox:outline_</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}outline_#2">#2</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
BaseX bug 10.7? error if inlined in outline</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:outline_</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$outlineItem</code><code class="as"> as </code><code class="type">item()?</code> )<code class="as"> as </code><code class="type">map(*)</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>outlineItem<code class="as"> as </code><code class="return-type">item()?</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*)</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline#2" title="Pdfbox3.xqm">pdfbox:outline#2</a></span></li></ul></details><details><summary>References 8 functions from 4 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions/map}entry#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions/map}merge#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}empty#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}getFirstChild#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem}getNextSibling#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}bookmark#2" title="Pdfbox3.xqm">pdfbox:bookmark#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}do-until#3" title="Pdfbox3.xqm">pdfbox:do-until#3</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}outline#2" title="Pdfbox3.xqm">pdfbox:outline#2</a></span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 20 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:outline_($pdf as item(),$outlineItem as item()?)
|
||
as map(*){
|
||
pdfbox:do-until(
|
||

|
||
map{"list":(),"this":$outlineItem},
|
||

|
||
function($input,$pos ) { 
|
||
let $bk:= pdfbox:bookmark($input?this,$pdf)
|
||
let $bk:= if($bk?hasChildren)
|
||
then let $kids:=pdfbox:outline($pdf,PDOutlineItem:getFirstChild($input?this))
|
||
return map:merge(($bk,map:entry("children",$kids)))
|
||
else $bk 
|
||
return map{
|
||
"list": ($input?list, $bk),
|
||
"this": PDOutlineItem:getNextSibling($input?this)}
|
||
},
|
||

|
||
function($output,$pos) { empty($output?this) } 
|
||
)
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:page-labels"></a><a id="{org.expkg_zone58.Pdfbox3}page-labels#1"></a><a href="#pdfbox:page-labels">4.22 </a>pdfbox:page-labels</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}page-labels#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
get pagelabels exist</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:page-labels</code>
|
||
(
|
||
<code class="arg">$pdf</code> )</div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type"></code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type"></code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getDocumentCatalog#1</span></li></ul></details><details><summary>Source ( 5 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:page-labels($pdf)
|
||
{
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:page-media-box"></a><a id="{org.expkg_zone58.Pdfbox3}page-media-box#2"></a><a href="#pdfbox:page-media-box">4.23 </a>pdfbox:page-media-box</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}page-media-box#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Return size of $pageNo (zero based)
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:page-media-box</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$pageNo</code><code class="as"> as </code><code class="type">xs:integer</code> )<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>pageNo<code class="as"> as </code><code class="return-type">xs:integer</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><dl><dt title="1">Tags</dt><dd><ul><li><span><span class="badge badge-pill badge-light">@result</span>:
|
||
<span>e.g. [0.0,0.0,168.0,239.52]</span></span></li></ul></dd></dl><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getPage#2</span></li></ul></details><details><summary>Source ( 6 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:page-media-box($pdf as item(), $pageNo as xs:integer)
|
||
as xs:string{
|
||
PDDocument:getPage($pdf, $pageNo)
|
||
=>PDPage:getMediaBox()
|
||
=>PDRectangle:toString()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:page-render"></a><a id="{org.expkg_zone58.Pdfbox3}page-render#3"></a><a href="#pdfbox:page-render">4.24 </a>pdfbox:page-render</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}page-render#3">#3</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Pdf page as image (zero is cover)
|
||
options.format="bmp jpg png gif" etc, options.scale= 1 is 72 dpi??</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:page-render</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$pageNo</code><code class="as"> as </code><code class="type">xs:integer</code>, <code class="arg">$options</code><code class="as"> as </code><code class="type">map(*)</code> )<code class="as"> as </code><code class="type">xs:base64Binary</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>pageNo<code class="as"> as </code><code class="return-type">xs:integer</code></li><li>options<code class="as"> as </code><code class="return-type">map(*)</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:base64Binary</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 5 functions from 4 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions/map}merge#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:java.io.ByteArrayOutputStream}new#0</span></li><li><span class="badge badge-warning" title="Externally defined">{java:java.io.ByteArrayOutputStream}toByteArray#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:javax.imageio.ImageIO}write#3</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.rendering.PDFRenderer}new#1</span></li></ul></details><details><summary>Source ( 11 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:page-render($pdf as item(),$pageNo as xs:integer,$options as map(*))
|
||
as xs:base64Binary{
|
||
let $options := map:merge(($options,map{"format":"jpg","scale":1}))
|
||
let $bufferedImage := PDFRenderer:new($pdf)
|
||
=>PDFRenderer:renderImage($pageNo,$options?scale)
|
||
let $bytes := Q{java:java.io.ByteArrayOutputStream}new()
|
||
let $_ := Q{java:javax.imageio.ImageIO}write($bufferedImage ,$options?format, $bytes)
|
||
return Q{java:java.io.ByteArrayOutputStream}toByteArray($bytes)
|
||
=>convert:integers-to-base64()
|
||

|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:page-text"></a><a id="{org.expkg_zone58.Pdfbox3}page-text#2"></a><a href="#pdfbox:page-text">4.25 </a>pdfbox:page-text</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}page-text#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
return text on $pageNo</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:page-text</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$pageNo</code><code class="as"> as </code><code class="type">xs:integer</code> )<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>pageNo<code class="as"> as </code><code class="return-type">xs:integer</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.text.PDFTextStripper}getText#2</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.text.PDFTextStripper}new#0</span></li></ul></details><details><summary>Source ( 9 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:page-text($pdf as item(), $pageNo as xs:integer)
|
||
as xs:string{
|
||
let $tStripper := (# db:wrapjava instance #) {
|
||
PDFTextStripper:new()
|
||
=> PDFTextStripper:setStartPage($pageNo)
|
||
=> PDFTextStripper:setEndPage($pageNo)
|
||
}
|
||
return (# db:checkstrings #) {PDFTextStripper:getText($tStripper,$pdf)}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:pdf-save"></a><a id="{org.expkg_zone58.Pdfbox3}pdf-save#2"></a><a href="#pdfbox:pdf-save">4.26 </a>pdfbox:pdf-save</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}pdf-save#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Save pdf $pdf to filesystem at $savepath , returns $savepath</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:pdf-save</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$savepath</code><code class="as"> as </code><code class="type">xs:string</code> )<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>savepath<code class="as"> as </code><code class="return-type">xs:string</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:java.io.File}new#1</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}save#2</span></li></ul></details><details><summary>Source ( 4 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:pdf-save($pdf as item(),$savepath as xs:string)
|
||
as xs:string{
|
||
PDDocument:save($pdf, File:new($savepath)),$savepath
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:property"></a><a id="{org.expkg_zone58.Pdfbox3}property#2"></a><a href="#pdfbox:property">4.27 </a>pdfbox:property</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}property#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
return value of $property for $pdf</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:property</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code>, <code class="arg">$property</code><code class="as"> as </code><code class="type">xs:string</code> )<code class="as"> as </code><code class="type">item()*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li><li>property<code class="as"> as </code><code class="return-type">xs:string</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">item() *</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#2" title="Pdfbox3.xqm">pdfbox:report#2</a></span></li></ul></details><details><summary>References 5 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2001/XMLSchema}QName#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}concat#3</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}error#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}exists#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}fold-left#3</span></li></ul></details><details><summary>Source ( 9 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:property($pdf as item(),$property as xs:string)
|
||
as item()*{
|
||
let $fns:= $pdfbox:property-map($property)
|
||
return if(exists($fns))
|
||
then fold-left($fns, 
|
||
$pdf, 
|
||
function($result,$this as function(*)){$result!$this(.)})
|
||
else error(xs:QName('pdfbox:property'),concat("Property '",$property,"' not defined."))
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:property-names"></a><a id="{org.expkg_zone58.Pdfbox3}property-names#0"></a><a href="#pdfbox:property-names">4.28 </a>pdfbox:property-names</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}property-names#0">#0</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
known property names sorted</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:property-names</code>
|
||
(
|
||
)<code class="as"> as </code><code class="type">xs:string*</code></div></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string *</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#1" title="Pdfbox3.xqm">pdfbox:report#1</a></span></li></ul></details><details><summary>Source ( 4 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:property-names() 
|
||
as xs:string*{
|
||
$pdfbox:property-map=>map:keys()=>sort()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:read-stream"></a><a id="{org.expkg_zone58.Pdfbox3}read-stream#2"></a><a href="#pdfbox:read-stream">4.29 </a>pdfbox:read-stream</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}read-stream#2">#2</a><span style="margin-left:1em"><span class="badge badge-dark" title="Private">P</span></span></span></p><dt class="label">Summary</dt><dd>
|
||
read next block from XMP stream</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:read-stream</code>
|
||
(
|
||
<code class="arg">$is</code>, <code class="arg">$read</code><code class="as"> as </code><code class="type">xs:string</code> )<code class="as"> as </code><code class="type">map(*)</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>is<code class="as"> as </code><code class="return-type"></code></li><li>read<code class="as"> as </code><code class="return-type">xs:string</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*)</code></li></ul></dd><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}metadata#1" title="Pdfbox3.xqm">pdfbox:metadata#1</a></span></li></ul></details><details><summary>References 6 functions from 5 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://basex.org/modules/convert}integers-to-base64#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2001/XMLSchema}byte#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2001/XMLSchema}int#1</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}subsequence#3</span></li><li><span class="badge badge-warning" title="Externally defined">{java:java.util.Arrays}copyOf#2</span></li><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.cos.COSInputStream}read#4</span></li></ul></details><details><summary>Annotations (1)</summary><table class="data"><tbody><tr><td><code class="function">%private</code></td><td><code class="arg">()</code></td></tr></tbody></table></details><details><summary>Source ( 8 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:read-stream($is,$read as xs:string)
|
||
as map(*){
|
||
let $blen:=4096
|
||
let $buff:=Q{java:java.util.Arrays}copyOf(array{xs:byte(0)},$blen)
|
||
let $n:= COSInputStream:read($is,$buff,xs:int(0),xs:int($blen))
|
||
let $data:=convert:integers-to-base64(subsequence($buff,1,$n))=>convert:binary-to-string()
|
||
return map{"n":$n, "data": $read || $data}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:report"></a><a id="{org.expkg_zone58.Pdfbox3}report#1"></a><a id="{org.expkg_zone58.Pdfbox3}report#2"></a><a href="#pdfbox:report">4.30 </a>pdfbox:report</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}report#1">#1</a><span style="margin-left:1em"></span></span><span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}report#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
summary CSV style info for all properties for $pdfpaths
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:report</code>
|
||
(
|
||
<code class="arg">$pdfpaths</code><code class="as"> as </code><code class="type">xs:string*</code> )<code class="as"> as </code><code class="type">map(*)</code></div><div class="proto"><code class="function">pdfbox:report</code>
|
||
(
|
||
<code class="arg">$pdfpaths</code><code class="as"> as </code><code class="type">item()*</code>, <code class="arg">$properties</code><code class="as"> as </code><code class="type">xs:string*</code> )<code class="as"> as </code><code class="type">map(*)</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdfpaths<code class="as"> as </code><code class="return-type">item()*</code></li><li>properties<code class="as"> as </code><code class="return-type">xs:string*</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">map(*)</code></li></ul></dd><dl><dt title="1">Tags</dt><dd><ul><li><span><a href="https://docs.basex.org/main/CSV_Functions#xquery">https://docs.basex.org/main/CSV_Functions#xquery</a></span></li></ul></dd></dl><details><summary>Referenced by 1 functions from 1 modules</summary><ul><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#1" title="Pdfbox3.xqm">pdfbox:report#1</a></span></li></ul></details><details><summary>References 8 functions from 3 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions/array}append#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}fold-left#3</span></li><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}string#1</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}close#1" title="Pdfbox3.xqm">pdfbox:close#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}open#1" title="Pdfbox3.xqm">pdfbox:open#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}property#2" title="Pdfbox3.xqm">pdfbox:property#2</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}property-names#0" title="Pdfbox3.xqm">pdfbox:property-names#0</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}report#2" title="Pdfbox3.xqm">pdfbox:report#2</a></span></li></ul></details><details><summary>Source ( 28 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:report($pdfpaths as xs:string*)
|
||
as map(*){
|
||
pdfbox:report($pdfpaths,pdfbox:property-names())
|
||
}</code></pre><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:report($pdfpaths as item()*, $properties as xs:string*)
|
||
as map(*){
|
||
map{"names": array{"path",$properties},
|
||

|
||
"records": for $path in $pdfpaths
|
||
let $name:=if($path instance of xs:base64Binary) then "binary" else $path
|
||
return try{
|
||
let $pdf:=pdfbox:open($path)
|
||
return (fold-left($properties,
|
||
array{$name},
|
||
function($result as array(*),$prop as xs:string){
|
||
array:append($result, string(pdfbox:property($pdf, $prop)))}
|
||
), pdfbox:close($pdf)
|
||
)
|
||
} catch *{
|
||
fold-left($properties,
|
||
array{$name},
|
||
function($result as array(*),$prop as xs:string){
|
||
array:append($result, "#ERROR")}
|
||
)
|
||
}
|
||

|
||
}
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:report-save"></a><a id="{org.expkg_zone58.Pdfbox3}report-save#2"></a><a href="#pdfbox:report-save">4.31 </a>pdfbox:report-save</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}report-save#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
convenience function to save report() data to file</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:report-save</code>
|
||
(
|
||
<code class="arg">$data</code><code class="as"> as </code><code class="type">map(*)</code>, <code class="arg">$dest</code><code class="as"> as </code><code class="type">xs:string</code> )<code class="as"> as </code><code class="type">empty-sequence</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>data<code class="as"> as </code><code class="return-type">map(*)</code></li><li>dest<code class="as"> as </code><code class="return-type">xs:string</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">empty-sequence</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 2 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://basex.org/modules/csv}serialize#2</span></li><li><span class="badge badge-warning" title="Externally defined">{http://expath.org/ns/file}write-text#2</span></li></ul></details><details><summary>Source ( 5 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:report-save($data as map(*),$dest as xs:string)
|
||
as empty-sequence(){
|
||
let $opts := map { "format":"xquery", "header":"yes", "separator" : "," }
|
||
return file:write-text($dest,csv:serialize($data,$opts))
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:specification"></a><a id="{org.expkg_zone58.Pdfbox3}specification#1"></a><a href="#pdfbox:specification">4.32 </a>pdfbox:specification</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}specification#1">#1</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
The version of the PDF specification used by $pdf e.g "1.4"
|
||
returned as string to avoid float rounding issues
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:specification</code>
|
||
(
|
||
<code class="arg">$pdf</code><code class="as"> as </code><code class="type">item()</code> )<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>pdf<code class="as"> as </code><code class="return-type">item()</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.pdmodel.PDDocument}getVersion#1</span></li></ul></details><details><summary>Source ( 4 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:specification($pdf as item())
|
||
as xs:string{
|
||
PDDocument:getVersion($pdf)=>xs:decimal()=>round(4)=>string()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:version"></a><a id="{org.expkg_zone58.Pdfbox3}version#0"></a><a href="#pdfbox:version">4.33 </a>pdfbox:version</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}version#0">#0</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
Version of Apache Pdfbox in use e.g. "3.0.4"</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:version</code>
|
||
(
|
||
)<code class="as"> as </code><code class="type">xs:string</code></div></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">xs:string</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 1 functions from 1 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{java:org.apache.pdfbox.util.Version}getVersion#0</span></li></ul></details><details><summary>Source ( 4 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:version()
|
||
as xs:string{
|
||
Q{java:org.apache.pdfbox.util.Version}getVersion()
|
||
}</code></pre></details></div><div class="div3"><h3><a id="pdfbox:with-pdf"></a><a id="{org.expkg_zone58.Pdfbox3}with-pdf#2"></a><a href="#pdfbox:with-pdf">4.34 </a>pdfbox:with-pdf</h3><p>Arities: <span style="margin-left:1em"><a href="#{org.expkg_zone58.Pdfbox3}with-pdf#2">#2</a><span style="margin-left:1em"></span></span></p><dt class="label">Summary</dt><dd>
|
||
"With-document" pattern: open pdf,apply $fn function, close pdf
|
||
creates a local pdfobject and ensures it is closed after use
|
||
e.g pdfbox:with-pdf("path...",pdfbox:page-text(?,5))
|
||
</dd><dt class="label">Signatures</dt><dd><div class="proto"><code class="function">pdfbox:with-pdf</code>
|
||
(
|
||
<code class="arg">$src</code><code class="as"> as </code><code class="type">xs:string</code>, <code class="arg">$fn</code><code class="as"> as </code><code class="type">function(item())as item()*</code> )<code class="as"> as </code><code class="type">item()*</code></div></dd><dt class="label">Parameters</dt><dd><ul><li>src<code class="as"> as </code><code class="return-type">xs:string</code></li><li>fn<code class="as"> as </code><code class="return-type">function(item())as item()*</code></li></ul></dd><dt class="label">Return</dt><dd><ul><li><code class="return-type">item() *</code></li></ul></dd><details><summary>Referenced by 0 functions from 0 modules</summary><ul></ul></details><details><summary>References 3 functions from 2 modules </summary><ul><li><span class="badge badge-warning" title="Externally defined">{http://www.w3.org/2005/xpath-functions}error#2</span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}close#1" title="Pdfbox3.xqm">pdfbox:close#1</a></span></li><li><span><a href="../../modules/F000001/index.html#{org.expkg_zone58.Pdfbox3}open#1" title="Pdfbox3.xqm">pdfbox:open#1</a></span></li></ul></details><details><summary>Source ( 11 lines)</summary><pre class="no-line-numbers" style="white-space:pre-wrap;"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">function pdfbox:with-pdf($src as xs:string,
|
||
$fn as function(item())as item()*)
|
||
as item()*{
|
||
let $pdf:=pdfbox:open($src)
|
||
return try{
|
||
$fn($pdf),pdfbox:close($pdf)
|
||
} catch *{
|
||
pdfbox:close($pdf),fn:error($err:code,$src || " " || $err:description)
|
||
}
|
||

|
||
}</code></pre></details></div></section><section id="namespaces"><h2>Namespaces</h2><p>The following namespaces are defined:</p><table class="data" style="float:none"><thead><tr><th>Prefix <span>-</span></th><th>Uri <span>-</span></th></tr></thead><tbody><tr><td>array</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/2005/xpath-functions/array</span></td></tr><tr><td>convert</td><td><span class="badge badge-warning" title="Externally defined">http://basex.org/modules/convert</span></td></tr><tr><td>COSInputStream</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.cos.COSInputStream</span></td></tr><tr><td>csv</td><td><span class="badge badge-warning" title="Externally defined">http://basex.org/modules/csv</span></td></tr><tr><td>db</td><td><span class="badge badge-warning" title="Externally defined">http://basex.org/modules/db</span></td></tr><tr><td>err</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/2005/xqt-errors</span></td></tr><tr><td>fetch</td><td><span class="badge badge-warning" title="Externally defined">http://basex.org/modules/fetch</span></td></tr><tr><td>File</td><td><span class="badge badge-warning" title="Externally defined">java:java.io.File</span></td></tr><tr><td>file</td><td><span class="badge badge-warning" title="Externally defined">http://expath.org/ns/file</span></td></tr><tr><td>fn</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/2005/xpath-functions</span></td></tr><tr><td>Loader</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.Loader</span></td></tr><tr><td>map</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/2005/xpath-functions/map</span></td></tr><tr><td>PageExtractor</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.multipdf.PageExtractor</span></td></tr><tr><td>PDDocument</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.PDDocument</span></td></tr><tr><td>PDDocumentCatalog</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.PDDocumentCatalog</span></td></tr><tr><td>PDDocumentInformation</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.PDDocumentInformation</span></td></tr><tr><td>PDDocumentOutline</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDDocumentOutline</span></td></tr><tr><td>pdfbox</td><td><span><a href="../../modules/F000001/index.html" title="Pdfbox3.xqm">org.expkg_zone58.Pdfbox3</a></span></td></tr><tr><td>PDFRenderer</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.rendering.PDFRenderer</span></td></tr><tr><td>PDFTextStripper</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.text.PDFTextStripper</span></td></tr><tr><td>PDMetadata</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.common.PDMetadata</span></td></tr><tr><td>PDOutlineItem</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem</span></td></tr><tr><td>PDPage</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.PDPage</span></td></tr><tr><td>PDPageLabelRange</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange</span></td></tr><tr><td>PDPageLabels</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.common.PDPageLabels</span></td></tr><tr><td>PDPageTree</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.pdmodel.PDPageTree</span></td></tr><tr><td>PDRectangle</td><td><span class="badge badge-warning" title="Externally defined">org.apache.pdfbox.pdmodel.common.PDRectangle</span></td></tr><tr><td>RandomAccessReadBuffer</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.io.RandomAccessReadBuffer</span></td></tr><tr><td>RandomAccessReadBufferedFile</td><td><span class="badge badge-warning" title="Externally defined">java:org.apache.pdfbox.io.RandomAccessReadBufferedFile</span></td></tr><tr><td>rdf</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/1999/02/22-rdf-syntax-ns#</span></td></tr><tr><td>xs</td><td><span class="badge badge-warning" title="Externally defined">http://www.w3.org/2001/XMLSchema</span></td></tr></tbody></table></section><div class="div2"><h2><a id="restxq"></a>6 RestXQ</h2><p>None</p></div><section id="source"><h2>Source Code</h2><pre style="white-space:pre-wrap;" class="line-numbers" data-src="plugins/line-numbers/index.html"><code class="language-xquery" data-prismjs-copy="Copy to clipboard">xquery version '3.1';
|
||
(:~ 
|
||
A BaseX 10.7+ interface to pdfbox3 https://pdfbox.apache.org/ , 
|
||
requires pdfbox jars on classpath, in lib/custom or xar
|
||
@note following the java source the terms outline and bookmark
|
||
refer to the same concept. Also label and (page)range are used interchangably
|
||
@note tested with pdfbox-app-3.0.5.jar
|
||
@see https://pdfbox.apache.org/download.cgi
|
||
@javadoc https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.5/
|
||
@author Andy Bunce 2025
|
||
:)
|
||

|
||
module namespace pdfbox="org.expkg_zone58.Pdfbox3";
|
||

|
||
declare namespace Loader ="java:org.apache.pdfbox.Loader"; 
|
||
declare namespace PDFTextStripper = "java:org.apache.pdfbox.text.PDFTextStripper";
|
||
declare namespace PDDocument ="java:org.apache.pdfbox.pdmodel.PDDocument";
|
||
declare namespace PDDocumentCatalog ="java:org.apache.pdfbox.pdmodel.PDDocumentCatalog";
|
||
declare namespace PDPageLabels ="java:org.apache.pdfbox.pdmodel.common.PDPageLabels";
|
||
declare namespace PDPageLabelRange="java:org.apache.pdfbox.pdmodel.common.PDPageLabelRange";
|
||

|
||
declare namespace PageExtractor ="java:org.apache.pdfbox.multipdf.PageExtractor";
|
||
declare namespace PDPage ="java:org.apache.pdfbox.pdmodel.PDPage";
|
||
declare namespace PDPageTree ="java:org.apache.pdfbox.pdmodel.PDPageTree";
|
||
declare namespace PDDocumentOutline ="java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDDocumentOutline";
|
||
declare namespace PDDocumentInformation ="java:org.apache.pdfbox.pdmodel.PDDocumentInformation";
|
||
declare namespace PDOutlineItem="java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem";
|
||
declare namespace PDFRenderer="java:org.apache.pdfbox.rendering.PDFRenderer";
|
||
declare namespace PDMetadata="java:org.apache.pdfbox.pdmodel.common.PDMetadata";
|
||
declare namespace COSInputStream="java:org.apache.pdfbox.cos.COSInputStream";
|
||

|
||

|
||
declare namespace rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#";
|
||

|
||

|
||
declare namespace RandomAccessReadBuffer="java:org.apache.pdfbox.io.RandomAccessReadBuffer";
|
||
declare namespace RandomAccessReadBufferedFile = "java:org.apache.pdfbox.io.RandomAccessReadBufferedFile";
|
||
declare namespace PDRectangle="org.apache.pdfbox.pdmodel.common.PDRectangle";
|
||

|
||
declare namespace File ="java:java.io.File";
|
||

|
||

|
||

|
||
(:~ "With-document" pattern: open pdf,apply $fn function, close pdf
|
||
creates a local pdfobject and ensures it is closed after use
|
||
e.g pdfbox:with-pdf("path...",pdfbox:page-text(?,5))
|
||
:)
|
||
declare function pdfbox:with-pdf($src as xs:string,
|
||
$fn as function(item())as item()*)
|
||
as item()*{
|
||
let $pdf:=pdfbox:open($src)
|
||
return try{
|
||
$fn($pdf),pdfbox:close($pdf)
|
||
} catch *{
|
||
pdfbox:close($pdf),fn:error($err:code,$src || " " || $err:description)
|
||
}
|
||

|
||
};
|
||

|
||

|
||
(:~ open pdf using fetch:binary, returns pdf object :)
|
||
declare function pdfbox:open($pdfsrc as item())
|
||
as item(){
|
||
pdfbox:open($pdfsrc, map{})
|
||
};
|
||

|
||
(:~ open pdf from file/url/binary, opts may have password , returns pdf object 
|
||
@param $pdfsrc a fetchable url or filepath, or xs:base64Binary item
|
||
@param $opts options options include map {"password":}
|
||
@note fetch:binary for https will use a lot of memory here
|
||
:)
|
||
declare function pdfbox:open($pdfsrc as item(), $opts as map(*))
|
||
as item(){
|
||
try{
|
||

|
||
if($pdfsrc instance of xs:base64Binary)
|
||
then Loader:loadPDF( $pdfsrc,string($opts?password))
|
||
else if(starts-with($pdfsrc,"http"))
|
||
then Loader:loadPDF( fetch:binary($pdfsrc),string($opts?password))
|
||
else Loader:loadPDF(RandomAccessReadBufferedFile:new($pdfsrc),string($opts?password))
|
||

|
||
} catch *{
|
||
let $loc:=if($pdfsrc instance of xs:base64Binary)
|
||
then "xs:base64Binary"
|
||
else $pdfsrc
|
||
return error(xs:QName("pdfbox:open"),"Failed PDF load " || $loc || " " || $err:description)
|
||
}
|
||
};
|
||

|
||
(:~ The version of the PDF specification used by $pdf e.g "1.4"
|
||
returned as string to avoid float rounding issues
|
||
:)
|
||
declare function pdfbox:specification($pdf as item())
|
||
as xs:string{
|
||
PDDocument:getVersion($pdf)=>xs:decimal()=>round(4)=>string()
|
||
};
|
||

|
||
(:~ Save pdf $pdf to filesystem at $savepath , returns $savepath :)
|
||
declare function pdfbox:pdf-save($pdf as item(),$savepath as xs:string)
|
||
as xs:string{
|
||
PDDocument:save($pdf, File:new($savepath)),$savepath
|
||
};
|
||

|
||
(:~ Create binary representation of $pdf object as xs:base64Binary :)
|
||
declare function pdfbox:binary($pdf as item())
|
||
as xs:base64Binary{
|
||
let $bytes:=Q{java:java.io.ByteArrayOutputStream}new()
|
||
let $_:=PDDocument:save($pdf, $bytes)
|
||
return Q{java:java.io.ByteArrayOutputStream}toByteArray($bytes)
|
||
=>convert:integers-to-base64()
|
||
};
|
||

|
||
(:~ Release any resources related to $pdf:)
|
||
declare function pdfbox:close($pdf as item())
|
||
as empty-sequence(){
|
||
(# db:wrapjava void #) {
|
||
PDDocument:close($pdf)
|
||
}
|
||
};
|
||

|
||
(:~ Number of pages in PDF:)
|
||
declare function pdfbox:number-of-pages($pdf as item())
|
||
as xs:integer{
|
||
PDDocument:getNumberOfPages($pdf)
|
||
};
|
||

|
||
(:~ Pdf page as image (zero is cover)
|
||
options.format="bmp jpg png gif" etc, options.scale= 1 is 72 dpi?? :)
|
||
declare function pdfbox:page-render($pdf as item(),$pageNo as xs:integer,$options as map(*))
|
||
as xs:base64Binary{
|
||
let $options := map:merge(($options,map{"format":"jpg","scale":1}))
|
||
let $bufferedImage := PDFRenderer:new($pdf)
|
||
=>PDFRenderer:renderImage($pageNo,$options?scale)
|
||
let $bytes := Q{java:java.io.ByteArrayOutputStream}new()
|
||
let $_ := Q{java:javax.imageio.ImageIO}write($bufferedImage ,$options?format, $bytes)
|
||
return Q{java:java.io.ByteArrayOutputStream}toByteArray($bytes)
|
||
=>convert:integers-to-base64()
|
||

|
||
};
|
||

|
||

|
||
(:~ property access map
|
||
keys are property names, 
|
||
values are sequences of functions to get property from $pdf object
|
||
:)
|
||
declare %private variable $pdfbox:property-map:=map{
|
||
"#pages": pdfbox:number-of-pages#1,
|
||

|
||
"#bookmarks": pdfbox:number-of-bookmarks#1,
|
||

|
||
"#labels": pdfbox:number-of-labels#1,
|
||

|
||
"specification":pdfbox:specification#1,
|
||

|
||
"title": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getTitle#1) ,
|
||

|
||
"author": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getAuthor#1 ),
|
||

|
||
"creator": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getCreator#1),
|
||

|
||
"producer": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getProducer#1),
|
||

|
||
"subject": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getSubject#1),
|
||

|
||
"keywords": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getKeywords#1),
|
||

|
||
"creationDate": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getCreationDate#1,
|
||
pdfbox:gregToISO#1),
|
||

|
||
"modificationDate": (PDDocument:getDocumentInformation#1,
|
||
PDDocumentInformation:getModificationDate#1,
|
||
pdfbox:gregToISO#1),
|
||
"labels": pdfbox:labels-as-strings#1 
|
||
};
|
||

|
||
(:~ known property names sorted :)
|
||
declare function pdfbox:property-names() 
|
||
as xs:string*{
|
||
$pdfbox:property-map=>map:keys()=>sort()
|
||
};
|
||

|
||
(:~ return value of $property for $pdf :)
|
||
declare function pdfbox:property($pdf as item(),$property as xs:string)
|
||
as item()*{
|
||
let $fns:= $pdfbox:property-map($property)
|
||
return if(exists($fns))
|
||
then fold-left($fns, 
|
||
$pdf, 
|
||
function($result,$this as function(*)){$result!$this(.)})
|
||
else error(xs:QName('pdfbox:property'),concat("Property '",$property,"' not defined."))
|
||
};
|
||

|
||
(:~ summary CSV style info for all properties for $pdfpaths 
|
||
:)
|
||
declare function pdfbox:report($pdfpaths as xs:string*)
|
||
as map(*){
|
||
pdfbox:report($pdfpaths,pdfbox:property-names())
|
||
};
|
||

|
||
(:~ summary CSV style info for named properties for $pdfpaths 
|
||
@see https://docs.basex.org/main/CSV_Functions#xquery
|
||
:)
|
||
declare function pdfbox:report($pdfpaths as item()*, $properties as xs:string*)
|
||
as map(*){
|
||
map{"names": array{"path",$properties},
|
||

|
||
"records": for $path in $pdfpaths
|
||
let $name:=if($path instance of xs:base64Binary) then "binary" else $path
|
||
return try{
|
||
let $pdf:=pdfbox:open($path)
|
||
return (fold-left($properties,
|
||
array{$name},
|
||
function($result as array(*),$prop as xs:string){
|
||
array:append($result, string(pdfbox:property($pdf, $prop)))}
|
||
), pdfbox:close($pdf)
|
||
)
|
||
} catch *{
|
||
fold-left($properties,
|
||
array{$name},
|
||
function($result as array(*),$prop as xs:string){
|
||
array:append($result, "#ERROR")}
|
||
)
|
||
}
|
||

|
||
}
|
||
};
|
||

|
||
(:~ convenience function to save report() data to file :)
|
||
declare function pdfbox:report-save($data as map(*),$dest as xs:string)
|
||
as empty-sequence(){
|
||
let $opts := map { "format":"xquery", "header":"yes", "separator" : "," }
|
||
return file:write-text($dest,csv:serialize($data,$opts))
|
||
};
|
||

|
||
(:~ number of outline items :)
|
||
declare function pdfbox:number-of-bookmarks($pdf as item())
|
||
as xs:integer{
|
||
let $xml:=pdfbox:outline-xml($pdf)
|
||
return count($xml//bookmark)
|
||
};
|
||

|
||
(:~ XMP metadata as "RDF" document
|
||
@note usually rdf:RDF root, but sometimes x:xmpmeta 
|
||
:)
|
||
declare function pdfbox:metadata($pdf as item())
|
||
as document-node(element(*))?
|
||
{
|
||
let $m:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getMetadata()
|
||
return if(exists($m))
|
||
then 
|
||
let $is:=PDMetadata:exportXMPMetadata($m)
|
||
return pdfbox:do-until(
|
||
map{"n":0,"data":""},
|
||

|
||
function($input,$pos ) { pdfbox:read-stream($is,$input?data)},
|
||

|
||
function($output,$pos) { $output?n eq -1 } 
|
||
)?data=>parse-xml()
|
||
else ()
|
||
};
|
||

|
||
(:~ read next block from XMP stream :)
|
||
declare %private function pdfbox:read-stream($is,$read as xs:string)
|
||
as map(*){
|
||
let $blen:=4096
|
||
let $buff:=Q{java:java.util.Arrays}copyOf(array{xs:byte(0)},$blen)
|
||
let $n:= COSInputStream:read($is,$buff,xs:int(0),xs:int($blen))
|
||
let $data:=convert:integers-to-base64(subsequence($buff,1,$n))=>convert:binary-to-string()
|
||
return map{"n":$n, "data": $read || $data}
|
||
};
|
||

|
||
(:~ outline for $pdf as map()* :)
|
||
declare function pdfbox:outline($pdf as item())
|
||
as map(*)*{
|
||
(# db:wrapjava some #) {
|
||
let $outline:=
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getDocumentOutline()
|
||

|
||
return if(exists($outline))
|
||
then pdfbox:outline($pdf,PDOutlineItem:getFirstChild($outline)) 
|
||
}
|
||
};
|
||

|
||
(:~ return bookmark info for children of $outlineItem as seq of maps :)
|
||
declare function pdfbox:outline($pdf as item(),$outlineItem as item()?)
|
||
as map(*)*{
|
||
let $find as map(*):=pdfbox:outline_($pdf ,$outlineItem)
|
||
return map:get($find,"list")
|
||
};
|
||

|
||
(:~ BaseX bug 10.7? error if inlined in outline :)
|
||
declare %private function pdfbox:outline_($pdf as item(),$outlineItem as item()?)
|
||
as map(*){
|
||
pdfbox:do-until(
|
||

|
||
map{"list":(),"this":$outlineItem},
|
||

|
||
function($input,$pos ) { 
|
||
let $bk:= pdfbox:bookmark($input?this,$pdf)
|
||
let $bk:= if($bk?hasChildren)
|
||
then let $kids:=pdfbox:outline($pdf,PDOutlineItem:getFirstChild($input?this))
|
||
return map:merge(($bk,map:entry("children",$kids)))
|
||
else $bk 
|
||
return map{
|
||
"list": ($input?list, $bk),
|
||
"this": PDOutlineItem:getNextSibling($input?this)}
|
||
},
|
||

|
||
function($output,$pos) { empty($output?this) } 
|
||
)
|
||
};
|
||

|
||
(:~ PDF outline in xml format :)
|
||
declare function pdfbox:outline-xml($pdf as item())
|
||
as element(outline)?{
|
||
let $outline:=pdfbox:outline($pdf)
|
||
return if(exists($outline))
|
||
then <outline>{$outline!pdfbox:bookmark-xml(.)}</outline>
|
||
else ()
|
||
};
|
||

|
||
(:~ Convert outline map to XML :)
|
||
declare %private function pdfbox:bookmark-xml($outline as map(*)*)
|
||
as element(bookmark)*
|
||
{
|
||
$outline!
|
||
<bookmark title="{?title}" index="{?index}">
|
||
{?children!pdfbox:bookmark-xml(.)}
|
||
</bookmark>
|
||
};
|
||

|
||
(:~ Return bookmark info for $bookmark
|
||
@return map{index:..,title:..,hasChildren:..}
|
||
:)
|
||
declare %private function pdfbox:bookmark($bookmark as item(),$pdf as item())
|
||
as map(*)
|
||
{
|
||
map{ 
|
||
"index": PDOutlineItem:findDestinationPage($bookmark,$pdf)=>pdfbox:find-page($pdf),
|
||
"title": (# db:checkstrings #) {PDOutlineItem:getTitle($bookmark)}
|
||
(:=>translate("<22>",""), :),
|
||
"hasChildren": PDOutlineItem:hasChildren($bookmark)
|
||
}
|
||
};
|
||

|
||

|
||
(:~ pageIndex of $page in $pdf :)
|
||
declare function pdfbox:find-page(
|
||
$page as item()? (: as java:org.apache.pdfbox.pdmodel.PDPage :),
|
||
$pdf as item())
|
||
as item()?
|
||
{
|
||
if(exists($page))
|
||
then PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPages()
|
||
=>PDPageTree:indexOf($page)
|
||
}; 
|
||

|
||
(:~ Return new PDF doc with pages from $start to $end as xs:base64Binary, (1 based) 
|
||
@param $start first page to include
|
||
@param $end last page to include
|
||
:)
|
||
declare function pdfbox:extract-range($pdf as item(), 
|
||
$start as xs:integer,$end as xs:integer)
|
||
as xs:base64Binary
|
||
{
|
||
let $a:=PageExtractor:new($pdf, $start, $end) =>PageExtractor:extract()
|
||
return (pdfbox:binary($a),pdfbox:close($a)) 
|
||
};
|
||

|
||
(:~ The number of labels defined in PDF :)
|
||
declare function pdfbox:number-of-labels($pdf as item())
|
||
as xs:integer
|
||
{
|
||
let $labels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return if(exists($labels)) 
|
||
then PDPageLabels:getPageRangeCount($labels)
|
||
else 0
|
||
};
|
||

|
||
(:~ pageLabel for every page from derived from page-ranges
|
||
The returned sequence will contain at MOST as much entries as the document has pages.
|
||
@see https://www.w3.org/TR/WCAG20-TECHS/PDF17.html#PDF17-examples
|
||
@see https://codereview.stackexchange.com/questions/286078/java-code-showing-page-labels-from-pdf-files
|
||
:)
|
||
declare function pdfbox:labels-by-page($pdf as item())
|
||
as xs:string*
|
||
{
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
=>PDPageLabels:getLabelsByPageIndices()
|
||
};
|
||

|
||
(:~ sequence of label ranges defined in PDF as formatted strings :)
|
||
declare function pdfbox:labels-as-strings($pdf as item())
|
||
as xs:string{
|
||
let $pagelabels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return $pagelabels
|
||
!(0 to pdfbox:number-of-pages($pdf)-1)
|
||
!pdfbox:label-as-string($pagelabels,.)=>string-join(",")
|
||

|
||
};
|
||

|
||
(:~ get pagelabels exist :)
|
||
declare function pdfbox:page-labels($pdf)
|
||
{
|
||
PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
};
|
||

|
||
(:~ label for $page formated as string :)
|
||
declare function pdfbox:label-as-string($pagelabels,$page as xs:integer)
|
||
as xs:string?{
|
||
let $label:=PDPageLabels:getPageLabelRange($pagelabels,$page)
|
||
return if(empty($label))
|
||
then ()
|
||
else
|
||
let $start:= PDPageLabelRange:getStart($label)
|
||
let $style := PDPageLabelRange:getStyle($label)
|
||
let $prefix:= PDPageLabelRange:getPrefix($label) 
|
||
return string-join(($page, 
|
||
if(empty($style)) then "-" else $style,
|
||
if(($start eq 1)) then "" else $start,
|
||
if(exists($prefix)) then '*' || $prefix (:TODO double " :)
|
||
))
|
||
};
|
||

|
||
(:~ sequence of maps for each label in :)
|
||
declare function pdfbox:labels-as-map($pdf as item())
|
||
as map(*)*{
|
||
let $pagelabels:=PDDocument:getDocumentCatalog($pdf)
|
||
=>PDDocumentCatalog:getPageLabels()
|
||
return $pagelabels
|
||
!(0 to pdfbox:number-of-pages($pdf)-1)
|
||
!pdfbox:label-as-map($pagelabels,.)
|
||
};
|
||

|
||
(:~ express label/page-range for $page as map :)
|
||
declare function pdfbox:label-as-map($pagelabels,$page as xs:integer)
|
||
as map(*)
|
||
{
|
||
let $label:=PDPageLabels:getPageLabelRange($pagelabels,$page)
|
||
return if(empty($label))
|
||
then ()
|
||
else map{
|
||
"index": $page,
|
||
"prefix": PDPageLabelRange:getPrefix($label),
|
||
"start": PDPageLabelRange:getStart($label),
|
||
"style": PDPageLabelRange:getStyle($label)
|
||
}
|
||
};
|
||

|
||

|
||

|
||
(:~ return text on $pageNo :)
|
||
declare function pdfbox:page-text($pdf as item(), $pageNo as xs:integer)
|
||
as xs:string{
|
||
let $tStripper := (# db:wrapjava instance #) {
|
||
PDFTextStripper:new()
|
||
=> PDFTextStripper:setStartPage($pageNo)
|
||
=> PDFTextStripper:setEndPage($pageNo)
|
||
}
|
||
return (# db:checkstrings #) {PDFTextStripper:getText($tStripper,$pdf)}
|
||
};
|
||

|
||
(:~ Return size of $pageNo (zero based)
|
||
@result e.g. [0.0,0.0,168.0,239.52]
|
||
:)
|
||
declare function pdfbox:page-media-box($pdf as item(), $pageNo as xs:integer)
|
||
as xs:string{
|
||
PDDocument:getPage($pdf, $pageNo)
|
||
=>PDPage:getMediaBox()
|
||
=>PDRectangle:toString()
|
||
};
|
||

|
||
(:~ Version of Apache Pdfbox in use e.g. "3.0.4" :)
|
||
declare function pdfbox:version()
|
||
as xs:string{
|
||
Q{java:org.apache.pdfbox.util.Version}getVersion()
|
||
};
|
||

|
||
(:~ Convert date :)
|
||
declare %private
|
||
function pdfbox:gregToISO($item as item()?)
|
||
as xs:string?{
|
||
if(exists($item))
|
||
then Q{java:java.util.GregorianCalendar}toZonedDateTime($item)=>string()
|
||
else ()
|
||
};
|
||

|
||
(:~ fn:do-until shim for BaseX 9+10 
|
||
if fn:do-until not found use hof:until, note: $pos always zero
|
||
:)
|
||
declare %private function pdfbox:do-until(
|
||
$input as item()*, 
|
||
$action as function(item()*, xs:integer) as item()*, 
|
||
$predicate as function(item()*, xs:integer) as xs:boolean? 
|
||
) as item()*
|
||
{
|
||
let $fn:=function-lookup(QName('http://www.w3.org/2005/xpath-functions','do-until'), 3)
|
||
return if(exists($fn))
|
||
then $fn($input,$action,$predicate)
|
||
else let $hof:=function-lookup(QName('http://basex.org/modules/hof','until'), 3)
|
||
return if(exists($hof))
|
||
then $hof($predicate(?,0),$action(?,0),$input)
|
||
else error(xs:QName('pdfbox:do-until'),"No implementation do-until found")
|
||

|
||
};
|
||
</code></pre></section></div></div><div class="footer"><p style="text-align:right">Generated by
|
||
<a href="https://github.com/Quodatum/xqdoca" target="_blank">xqDocA <span>0.9.1</span></a>
|
||
on <span title="2025-06-03T22:34:04.782+01:00">Tuesday, 3rd June 2025</span></p></div><script src="../../resources/prism/1.29.0/prism.js" type="text/javascript"></script><script src="../../resources/xqdoca.js" type="text/javascript"></script></body></html> |