[mod] update to pdfbox 3.0.5
This commit is contained in:
parent
196ffa7526
commit
a3bef9d6f4
7 changed files with 54 additions and 61 deletions
8
doc.md
8
doc.md
|
@ -78,10 +78,10 @@ let $text := pdfbox:page-text($pdf, 1) (: Extract text from page 1 :)
|
|||
---
|
||||
|
||||
### Rendering a Page as an Image
|
||||
You can render a PDF page as an image using the `pdfbox:page-image` function. Supported formats include `jpg`, `png`, `bmp`, and `gif`.
|
||||
You can render a PDF page as an image using the `pdfbox:page-render` function. Supported formats include `jpg`, `png`, `bmp`, and `gif`.
|
||||
|
||||
```xquery
|
||||
let $image := pdfbox:page-image($pdf, 1, map{"format": "png", "scale": 2})
|
||||
let $image := pdfbox:page-render($pdf, 1, map{"format": "png", "scale": 2})
|
||||
```
|
||||
|
||||
- `format`: The image format (default is `jpg`).
|
||||
|
@ -90,10 +90,10 @@ let $image := pdfbox:page-image($pdf, 1, map{"format": "png", "scale": 2})
|
|||
---
|
||||
|
||||
### Extracting a Range of Pages
|
||||
To extract a range of pages from a PDF, use the `pdfbox:extract` function.
|
||||
To extract a range of pages from a PDF, use the `pdfbox:extract-range` function.
|
||||
|
||||
```xquery
|
||||
let $extracted := pdfbox:extract($pdf, 1, 3) (: Extract pages 1 to 3 :)
|
||||
let $extracted := pdfbox:extract-range($pdf, 1, 3) (: Extract pages 1 to 3 :)
|
||||
```
|
||||
|
||||
The result is a new PDF document in binary format.
|
||||
|
|
14
package.json
14
package.json
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"name": "pdfbox",
|
||||
"version": "0.2.7",
|
||||
"version": "0.3.1",
|
||||
"description": "A BaseX interface to Apache Pdfbox version 3",
|
||||
"main": "src/Pdfbox3.xqm",
|
||||
"homepage": "https://github.com/expkg-zone58/pdfbox#readme",
|
||||
|
@ -8,7 +8,7 @@
|
|||
"doc": "docs"
|
||||
},
|
||||
"scripts": {
|
||||
"test": "%BASEX10%/bin/basex -Wt tests",
|
||||
"test": "%BASEX10%/bin/basex -Wt tests",
|
||||
"docs": "xqdoca"
|
||||
},
|
||||
"keywords": [
|
||||
|
@ -22,11 +22,13 @@
|
|||
"expkg_zone58": {
|
||||
"namespace": "org.expkg_zone58.Pdfbox3",
|
||||
"main-class": "org.apache.pdfbox.pdmodel.PDDocument",
|
||||
"manifest-jar" :"pdfbox-3.0.4.jar",
|
||||
"output" : "dist/pdfbox-3.0.5.fat.jar",
|
||||
"maven2": [
|
||||
"org.apache.pdfbox:pdfbox:3.0.4",
|
||||
"org.apache.pdfbox:pdfbox-io:3.0.4",
|
||||
"org.apache.pdfbox:fontbox:3.0.4",
|
||||
"commons-logging:commons-logging:1.3.4"
|
||||
"org.apache.pdfbox:pdfbox:3.0.5",
|
||||
"org.apache.pdfbox:pdfbox-io:3.0.5",
|
||||
"org.apache.pdfbox:fontbox:3.0.5",
|
||||
"commons-logging:commons-logging:1.3.5"
|
||||
]
|
||||
|
||||
}
|
||||
|
|
|
@ -41,7 +41,7 @@ import module namespace pdfbox="org.expkg_zone58.Pdfbox3";
|
|||
|
||||
pdfbox:with-pdf("...path/to/pdf.pdf",
|
||||
function($pdf){
|
||||
(1 to pdfbox:page-count($pdf))!pdfbox:page-text($pdf,.)
|
||||
(1 to pdfbox:number-of-pages($pdf))!pdfbox:page-text($pdf,.)
|
||||
}
|
||||
)
|
||||
```
|
||||
|
|
|
@ -9,6 +9,8 @@ declare namespace pkg='http://expath.org/ns/pkg';
|
|||
declare variable $build:archive-opts:= map { "format" : "zip", "algorithm" : "deflate" };
|
||||
|
||||
declare variable $build:base:= file:resolve-path("../",static-base-uri())=>trace("base ");
|
||||
|
||||
(:~ load "npm style" package.json :)
|
||||
declare variable $build:PKG:=json:doc(file:resolve-path("package.json",$build:base),map{"format":"xquery"});
|
||||
|
||||
(:~ return binary for fat jar from jars in $input-dir
|
||||
|
|
|
@ -3,29 +3,18 @@ import module namespace build = 'urn:quodatum:build1' at 'build.xqm';
|
|||
|
||||
declare variable $base:= file:resolve-path("../",static-base-uri())=>trace("base ");
|
||||
|
||||
declare variable $maven-urls := (
|
||||
"org/apache/pdfbox/pdfbox/3.0.4/pdfbox-3.0.4.jar",
|
||||
"org/apache/pdfbox/pdfbox-io/3.0.4/pdfbox-io-3.0.4.jar",
|
||||
"org/apache/pdfbox/fontbox/3.0.4/fontbox-3.0.4.jar",
|
||||
"commons-logging/commons-logging/1.3.4/commons-logging-1.3.4.jar"
|
||||
);
|
||||
|
||||
let $config :=map {
|
||||
"manifest-jar" : "pdfbox-3.0.4.jar",
|
||||
"input-dir" : "jars/",
|
||||
"output" : "dist/pdfbox-3.0.4.fat.jar",
|
||||
"main-class": "org.expkg_zone58.Pdfbox3"
|
||||
}
|
||||
|
||||
let $jar-path:=file:resolve-path($config?input-dir,$base)=>trace("jar: ")
|
||||
let $_:=build:maven-download($maven-urls,$jar-path)
|
||||
let $fat-jar := build:fatjar-from-folder($jar-path,$config?manifest-jar)
|
||||
let $jar-path:=$build:base || "jars/"=>trace("jar: ")
|
||||
let $_:=build:maven-download($build:PKG?expkg_zone58?maven2=>array:flatten(),
|
||||
$build:base || "jars/")
|
||||
|
||||
let $fat-jar:=build:update-manifest($fat-jar, $config?main-class)
|
||||
let $name:=replace($config?main-class,"\.","/") || ".xqm"
|
||||
let $fat-jar := build:fatjar-from-folder($jar-path,$build:PKG?expkg_zone58?manifest-jar)
|
||||
|
||||
let $fat-jar:=build:update-manifest($fat-jar, $build:PKG?expkg_zone58?main-class)
|
||||
let $name:=replace($build:PKG?expkg_zone58?main-class,"\.","/") || ".xqm"
|
||||
let $content:=file:read-binary($base || "src/Pdfbox3.xqm")
|
||||
let $fat-jar:=archive:update($fat-jar, $name,$content)
|
||||
let $output-file := file:resolve-path($config?output,$base)
|
||||
let $output-file := file:resolve-path($build:PKG?expkg_zone58?output,$base)
|
||||
return (build:write-binary($output-file, $fat-jar),
|
||||
trace($output-file,"fat jar: "))
|
||||
|
|
@ -1,10 +1,10 @@
|
|||
xquery version '3.1';
|
||||
(:~
|
||||
pdfbox 3.0 https://pdfbox.apache.org/ BaseX 10.7+ interface library,
|
||||
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-3.0.4.jar
|
||||
@see download https://pdfbox.apache.org/download.cgi
|
||||
@javadoc https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.4/
|
||||
tested with pdfbox-app-3.0.5.jar
|
||||
@see <a href="https://pdfbox.apache.org/download.cgi">download</a>
|
||||
@javadoc https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.5/
|
||||
@author Andy Bunce 2025
|
||||
:)
|
||||
|
||||
|
@ -16,7 +16,7 @@ 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 PageExtractor ="java:org.apache.pdfbox.multipdf.PageExtractor";
|
||||
declare namespace PDPage ="org.apache.pdfbox.pdmodel.PDPage";
|
||||
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";
|
||||
|
@ -54,8 +54,8 @@ pdfbox:open($pdfsrc, map{})
|
|||
};
|
||||
|
||||
(:~ open pdf from file/url/binary, opts may have password , returns pdf object
|
||||
@param $pdfsrc a fetchable url or a xs:base64Binary
|
||||
@param $opts map {"password":}
|
||||
@param $pdfsrc a fetchable url or filepath, or xs:base64Binary item
|
||||
@param $opts options otionally with map {"password":}
|
||||
:)
|
||||
declare function pdfbox:open($pdfsrc as item(), $opts as map(*))
|
||||
as item(){
|
||||
|
@ -75,7 +75,7 @@ as item(){
|
|||
}
|
||||
};
|
||||
|
||||
(:~ the version of the PDF specification used by $pdf e.g "1.4"
|
||||
(:~ 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())
|
||||
|
@ -83,13 +83,13 @@ as xs:string{
|
|||
PDDocument:getVersion($pdf)=>xs:decimal()=>round(4)=>string()
|
||||
};
|
||||
|
||||
(:~ save pdf $pdf to filesystem at $savepath , returns $savepath :)
|
||||
(:~ Save pdf $pdf to filesystem at $savepath , returns $savepath :)
|
||||
declare function pdfbox:save($pdf as item(),$savepath as xs:string)
|
||||
as xs:string{
|
||||
PDDocument:save($pdf, File:new($savepath)),$savepath
|
||||
};
|
||||
|
||||
(:~ $pdf as xs:base64Binary :)
|
||||
(:~ Create binary representation of $pdf as xs:base64Binary :)
|
||||
declare function pdfbox:binary($pdf as item())
|
||||
as xs:base64Binary{
|
||||
let $bytes:=Q{java:java.io.ByteArrayOutputStream}new()
|
||||
|
@ -98,7 +98,7 @@ as xs:base64Binary{
|
|||
=>convert:integers-to-base64()
|
||||
};
|
||||
|
||||
(:~ release references to $pdf:)
|
||||
(:~ Release any resources related to $pdf:)
|
||||
declare function pdfbox:close($pdf as item())
|
||||
as empty-sequence(){
|
||||
(# db:wrapjava void #) {
|
||||
|
@ -106,15 +106,15 @@ as empty-sequence(){
|
|||
}
|
||||
};
|
||||
|
||||
(:~ number of pages in PDF:)
|
||||
declare function pdfbox:page-count($pdf as item())
|
||||
(:~ Number of pages in PDF:)
|
||||
declare function pdfbox:number-of-pages($pdf as item())
|
||||
as xs:integer{
|
||||
PDDocument:getNumberOfPages($pdf)
|
||||
};
|
||||
|
||||
(:~ pdf page as image (zero is cover)
|
||||
(:~ Pdf page as image (zero is cover)
|
||||
options.format="bmp jpg png gif" etc, options.scale= 1 is 72 dpi?? :)
|
||||
declare function pdfbox:page-image($pdf as item(),$pageNo as xs:integer,$options as map(*))
|
||||
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)
|
||||
|
@ -130,7 +130,7 @@ as xs:base64Binary{
|
|||
values are sequences of functions to get property from $pdf object
|
||||
:)
|
||||
declare %private variable $pdfbox:property-map:=map{
|
||||
"pageCount": pdfbox:page-count#1,
|
||||
"pageCount": pdfbox:number-of-pages#1,
|
||||
|
||||
"hasOutline": pdfbox:hasOutline#1,
|
||||
|
||||
|
@ -166,7 +166,7 @@ declare %private variable $pdfbox:property-map:=map{
|
|||
};
|
||||
|
||||
(:~ known property names sorted :)
|
||||
declare function pdfbox:defined-properties()
|
||||
declare function pdfbox:property-names()
|
||||
as xs:string*{
|
||||
$pdfbox:property-map=>map:keys()=>sort()
|
||||
};
|
||||
|
@ -275,7 +275,7 @@ as map(*){
|
|||
)
|
||||
};
|
||||
|
||||
(:~ outline as xml :)
|
||||
(:~ PDF outline in xml format :)
|
||||
declare function pdfbox:outline-xml($pdf as item())
|
||||
as element(outline)?{
|
||||
let $outline:=pdfbox:outline($pdf)
|
||||
|
@ -294,8 +294,8 @@ as element(bookmark)*
|
|||
</bookmark>
|
||||
};
|
||||
|
||||
(:~ return bookmark info for children of $outlineItem
|
||||
@return map like{index:,title:,hasChildren:}
|
||||
(:~ return bookmark info for $bookmark
|
||||
@return map{index:..,title:..,hasChildren:..}
|
||||
:)
|
||||
declare %private function pdfbox:bookmark($bookmark as item(),$pdf as item())
|
||||
as map(*)
|
||||
|
@ -321,8 +321,8 @@ as item()?
|
|||
=>PDPageTree:indexOf($page)
|
||||
};
|
||||
|
||||
(:~ new PDF doc from 1 based page range as xs:base64Binary :)
|
||||
declare function pdfbox:extract($pdf as item(),
|
||||
(:~ Return new extract PDF doc as xs:base64Binary, using a 1 based page range :)
|
||||
declare function pdfbox:extract-range($pdf as item(),
|
||||
$start as xs:integer,$end as xs:integer)
|
||||
as xs:base64Binary
|
||||
{
|
||||
|
|
|
@ -9,7 +9,7 @@ declare variable $test:base:=file:base-dir()=>file:parent();
|
|||
declare %unit:test
|
||||
function test:pdfbox-version(){
|
||||
let $v:= pdfbox:version()=>trace("VER: ")
|
||||
return unit:assert-equals($v,"3.0.4")
|
||||
return unit:assert-equals($v,"3.0.5")
|
||||
};
|
||||
|
||||
declare %unit:test
|
||||
|
@ -22,7 +22,7 @@ function test:specification(){
|
|||
declare %unit:test
|
||||
function test:page-count(){
|
||||
let $pdf:=test:open("samples.pdf/BaseX100.pdf")
|
||||
let $pages:=pdfbox:page-count($pdf)
|
||||
let $pages:=pdfbox:number-of-pages($pdf)
|
||||
return unit:assert-equals($pages,521)
|
||||
};
|
||||
|
||||
|
@ -53,7 +53,7 @@ function test:labels(){
|
|||
|
||||
let $labels:=pdfbox:labels($pdf)
|
||||
return (
|
||||
unit:assert-equals(count($labels),pdfbox:page-count($pdf)),
|
||||
unit:assert-equals(count($labels),pdfbox:number-of-pages($pdf)),
|
||||
unit:assert($labels[1]="i") ,
|
||||
unit:assert($labels[27]="1")
|
||||
)
|
||||
|
@ -63,7 +63,7 @@ declare %unit:test
|
|||
function test:extract(){
|
||||
let $pdf:=test:open("samples.pdf/BaseX100.pdf")
|
||||
let $dest:=file:create-temp-file("test",".pdf")=>trace("DEST: ")
|
||||
let $bin:=pdfbox:extract($pdf,2,12)
|
||||
let $bin:=pdfbox:extract-range($pdf,2,12)
|
||||
return unit:assert(true())
|
||||
};
|
||||
|
||||
|
@ -77,7 +77,7 @@ let $pdf:=test:open("samples.pdf/BaseX100.pdf")
|
|||
declare %unit:test
|
||||
function test:page-image(){
|
||||
let $pdf:=test:open("samples.pdf/BaseX100.pdf")
|
||||
let $image:=pdfbox:page-image($pdf,0,map{})
|
||||
let $image:=pdfbox:page-render($pdf,0,map{})
|
||||
return unit:assert(true())
|
||||
};
|
||||
|
||||
|
@ -94,7 +94,7 @@ declare %unit:test
|
|||
function test:with-url(){
|
||||
let $url:="https://files.basex.org/publications/Gath%20et%20al.%20%5b2009%5d,%20INEX%20Efficiency%20Track%20meets%20XQuery%20Full%20Text%20in%20BaseX.pdf"
|
||||
|
||||
let $count:=pdfbox:with-pdf($url,pdfbox:page-count#1)
|
||||
let $count:=pdfbox:with-pdf($url,pdfbox:number-of-pages#1)
|
||||
return unit:assert-equals($count,6)
|
||||
};
|
||||
|
||||
|
@ -141,13 +141,13 @@ function test:property(){
|
|||
declare %unit:test("expected", "pdfbox:property")
|
||||
function test:property-bad(){
|
||||
let $pdf:=test:open("samples.pdf/BaseX100.pdf")
|
||||
let $title:=pdfbox:property($pdf, "totle")
|
||||
let $title:=pdfbox:property($pdf, "badname")
|
||||
return unit:assert(exists($title))
|
||||
};
|
||||
(:~ Test for pdfbox:defined-properties function :)
|
||||
(:~ Test for pdfbox:property-names function :)
|
||||
declare %unit:test
|
||||
function test:defined-properties(){
|
||||
let $properties:=pdfbox:defined-properties()
|
||||
let $properties:=pdfbox:property-names()
|
||||
return unit:assert(exists($properties))
|
||||
};
|
||||
|
||||
|
|
Loading…
Add table
Reference in a new issue