1
0
Fork 0

[mod] 0.3.6

This commit is contained in:
Andy Bunce 2025-06-01 18:00:17 +01:00
parent a3bef9d6f4
commit ed84a3b342
5 changed files with 64 additions and 14 deletions

View file

@ -1,3 +1,9 @@
# 0.3.6 2025-05-31
* Add metadata function
* rename page-size->page-media-box
# 0.3.1 2025-05-28
* update to Apache pdfbox to 3.0.5
* API name changes e.g. page-count->number-of-pages
# 0.2.7 2025-02-18
* reduce memory use
* add open from xs:base64Binary

4
doc.md
View file

@ -162,10 +162,10 @@ let $labels := pdfbox:labels($pdf)
---
### Getting Page Size
To get the size of a specific page, use the `pdfbox:page-size` function.
To get the size of a specific page, use the `pdfbox:page-media-box` function.
```xquery
let $size := pdfbox:page-size($pdf, 1) (: Get size of page 1 :)
let $size := pdfbox:page-media-box($pdf, 1) (: Get size of page 1 :)
```
---

View file

@ -1,6 +1,6 @@
{
"name": "pdfbox",
"version": "0.3.1",
"version": "0.3.6",
"description": "A BaseX interface to Apache Pdfbox version 3",
"main": "src/Pdfbox3.xqm",
"homepage": "https://github.com/expkg-zone58/pdfbox#readme",
@ -9,7 +9,8 @@
},
"scripts": {
"test": "%BASEX10%/bin/basex -Wt tests",
"docs": "xqdoca"
"docs": "xqdoca",
"build": "%BASEX10%/bin/basex scripts/make-xar.xq"
},
"keywords": [
"pdf",
@ -22,7 +23,7 @@
"expkg_zone58": {
"namespace": "org.expkg_zone58.Pdfbox3",
"main-class": "org.apache.pdfbox.pdmodel.PDDocument",
"manifest-jar" :"pdfbox-3.0.4.jar",
"manifest-jar" :"pdfbox-3.0.5.jar",
"output" : "dist/pdfbox-3.0.5.fat.jar",
"maven2": [
"org.apache.pdfbox:pdfbox:3.0.5",

View file

@ -20,12 +20,12 @@ The features focus on extracting information from PDFs rather than creation or e
* save pdf page range to a new pdf.
* save image of rendered pdf page.
* open PDF with password
* read XMP metadata
* Page size information
* support for xs:base64Binary in function inputs and outputs to facilitate database and store usage.
### Not supported:
* creating completely new PDFs
* Page size information
* XMP processing
* creating PDFs with new content
* Form processing
## Documentation

View file

@ -3,7 +3,7 @@ xquery version '3.1';
A BaseX 10.7+ interface to pdfbox 3.0 https://pdfbox.apache.org/ ,
requires pdfbox jars on classpath, i.e. in custom or xar
tested with pdfbox-app-3.0.5.jar
@see <a href="https://pdfbox.apache.org/download.cgi">download</a>
@see https://pdfbox.apache.org/download.cgi
@javadoc https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.5/
@author Andy Bunce 2025
:)
@ -22,6 +22,12 @@ declare namespace PDDocumentOutline ="java:org.apache.pdfbox.pdmodel.interactive
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";
@ -89,7 +95,7 @@ as xs:string{
PDDocument:save($pdf, File:new($savepath)),$savepath
};
(:~ Create binary representation of $pdf as xs:base64Binary :)
(:~ 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()
@ -125,6 +131,7 @@ as xs:base64Binary{
};
(:~ property access map
keys are property names,
values are sequences of functions to get property from $pdf object
@ -233,6 +240,37 @@ as xs:boolean{
=>exists()
};
(:~ XMP metadata as "RDF" document
@note usually rdf:RDF root, but sometimes x:xmpmeta
:)
declare function pdfbox:metadata($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(*)*{
@ -321,7 +359,10 @@ as item()?
=>PDPageTree:indexOf($page)
};
(:~ Return new extract PDF doc as xs:base64Binary, using a 1 based page range :)
(:~ 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
@ -356,8 +397,10 @@ as xs:string{
return (# db:checkstrings #) {PDFTextStripper:getText($tStripper,$pdf)}
};
(:~ return size of $pageNo (zero is cover :)
declare function pdfbox:page-size($pdf as item(), $pageNo as xs:integer)
(:~ 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()
@ -380,7 +423,7 @@ as xs:string?{
};
(:~ fn:do-until shim for BaseX 9+10
if fn:do-until not found use hof:until
if fn:do-until not found use hof:until, note: $pos always zero
:)
declare %private function pdfbox:do-until(
$input as item()*,