1
0
Fork 0

[mod] download jars

This commit is contained in:
Andy Bunce 2025-01-27 16:56:32 +00:00
parent 52942a5ce1
commit 0c3e9482cb
15 changed files with 32 additions and 102 deletions

1
.gitignore vendored
View file

@ -1,2 +1,3 @@
data/
dist/
docs/xqdoc/

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

17
scripts/download.xq Normal file
View file

@ -0,0 +1,17 @@
import module namespace build = 'urn:quodatum:build1' at 'build.xqm';
declare variable $files := (
"https://repo1.maven.org/maven2/org/apache/pdfbox/pdfbox/3.0.4/pdfbox-3.0.4.jar",
"https://repo1.maven.org/maven2/org/apache/pdfbox/pdfbox-io/3.0.4/pdfbox-io-3.0.4.jar",
"https://repo1.maven.org/maven2/org/apache/pdfbox/fontbox/3.0.4/fontbox-3.0.4.jar",
"https://repo1.maven.org/maven2/commons-logging/commons-logging/1.3.4/commons-logging-1.3.4.jar"
);
let $base:= file:resolve-path("../",static-base-uri())
let $target:=file:resolve-path("jars/",$base)
for $f in $files
let $n:=replace($f,"^.*/","") =>trace("N")
return file:write-binary($target || $n, fetch:binary($f))

View file

@ -8,7 +8,7 @@ let $config :=map {
"base": file:resolve-path("../",static-base-uri()),
"manifest-jar" : "pdfbox-3.0.4.jar",
"input-dir" : "jars/",
"output" : "lib/pdfbox-3.0.4.fat.jar",
"output" : "dist/pdfbox-3.0.4.fat.jar",
"main-class": "org.expkg_zone58.Pdfbox3"
}
let $jar-path:=file:resolve-path($config?input-dir,$config?base=>trace("base "))=>trace("jar: ")
@ -16,7 +16,7 @@ let $fat-jar := build:fatjar-from-folder($jar-path,$config?manifest-jar)
let $fat-jar:=build:update-manifest($fat-jar, $config?main-class)
let $name:=replace($config?main-class,"\.","/") || ".xqm"
let $content:=file:read-binary($jar-path || "Pdfbox3.xqm")
let $content:=file:read-binary($config?base || "src/Pdfbox3.xqm")
let $fat-jar:=archive:update($fat-jar, $name,$content)
let $output-file := file:resolve-path($config?output,$config?base)
return (file:write-binary($output-file, $fat-jar),

View file

@ -1,9 +1,9 @@
xquery version '3.1';
(:~
pdfbox 3.0 https://pdfbox.apache.org/ BaseX 10.7+ interface library,
requires pdfbox jar on classpath, tested with pdfbox-app-3.0.3.jar
requires pdfbox jar on classpath, 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/3.0.3/
@javadoc https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.4/
:)
module namespace pdfbox="org.expkg_zone58.Pdfbox3";
@ -11,32 +11,26 @@ module namespace pdfbox="org.expkg_zone58.Pdfbox3";
declare namespace Loader ="java:org.apache.pdfbox.Loader";
declare namespace PDFTextStripper = "java:org.apache.pdfbox.text.PDFTextStripper";
(:~
@see https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.0/org/apache/pdfbox/pdmodel/PDDocument.html
:)
(:~ @javadoc org/apache/pdfbox/pdmodel/PDDocument.html :)
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";
(:~
@see https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.0/org/apache/pdfbox/multipdf/PageExtractor.html
:)
(:~ @javadoc org/apache/pdfbox/multipdf/PageExtractor.html :)
declare namespace PageExtractor ="java:org.apache.pdfbox.multipdf.PageExtractor";
(:~
@see https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.0/org/apache/pdfbox/pdmodel/PDPageTree.html
:)
(:~ @javadoc org/apache/pdfbox/pdmodel/PDPageTree.html :)
declare namespace PDPageTree ="java:org.apache.pdfbox.pdmodel.PDPageTree";
(:~
@see https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.2/org/apache/pdfbox/pdmodel/interactive/documentnavigation/outline/PDDocumentOutline.html
@javadoc org/apache/pdfbox/pdmodel/interactive/documentnavigation/outline/PDDocumentOutline.html
:)
declare namespace PDDocumentOutline ="java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDDocumentOutline";
declare namespace PDDocumentInformation ="java:org.apache.pdfbox.pdmodel.PDDocumentInformation";
(:~
@see https://javadoc.io/static/org.apache.pdfbox/pdfbox/3.0.0/org/apache/pdfbox/pdmodel/interactive/documentnavigation/outline/PDOutlineItem.html
@javadoc org/apache/pdfbox/pdmodel/interactive/documentnavigation/outline/PDOutlineItem.html
:)
declare namespace PDOutlineItem="java:org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem";
declare namespace PDFRenderer="java:org.apache.pdfbox.rendering.PDFRenderer";
@ -55,7 +49,7 @@ as item(){
Loader:loadPDF( RandomAccessReadBufferedFile:new($pdfpath))
};
(:~ the PDF specification version this $pdf conforms to.:)
(:~ the version of the PDF specification used by $pdf :)
declare function pdfbox:pdfVersion($pdf as item())
as xs:float{
PDDocument:getVersion($pdf)
@ -179,14 +173,14 @@ declare function pdfbox:outx($page ,$document)
return $pageNumber
};
(:~ pageIndex of $page in $document :)
(:~ pageIndex of $page in $pdf :)
declare function pdfbox:pageIndex(
$page as item()? (: as java:org.apache.pdfbox.pdmodel.PDPage :),
$document)
$pdf)
as item()?
{
if(exists($page))
then PDDocument:getDocumentCatalog($document)
then PDDocument:getDocumentCatalog($pdf)
=>PDDocumentCatalog:getPages()
=>PDPageTree:indexOf($page)
};

View file

@ -1,5 +0,0 @@
xquery version '3.1';
(:~ look for pagenos in pdf text
pagenos:page-report($doc )=>pagenos:inverted-map()
:)
module namespace pagenos = 'urn:pageno';

View file

@ -3,7 +3,7 @@ xquery version '3.1';
pdfscrape:page-report($doc )=>pdfscrape:inverted-map()
:)
module namespace pdfscrape = 'urn:pdfscrape';
import module namespace pdfbox="urn:expkg-zone58:pdfbox3" at "pdfbox3.xqm";
import module namespace pdfbox="org.expkg_zone58.Pdfbox3" ;
(:~ page number regex
@todo last line and roman

View file

@ -1,26 +0,0 @@
(: test use of pageIndex :)
import module namespace pdfbox="urn:expkg-zone58:pdfbox3" at "../lib/pdfbox3.xqm";
declare variable $base:=file:base-dir();
declare function local:go($doc,$pdf as element(pdf)){
let $range:=$pdf/@pages/tokenize(.,"")
let $start:=$range[1]
let $end:=if(count($range) eq 1) then $range[1] else $range[2]
return ``[ `{$start}` ;;; `{ $end }` ]``
};
let $src:="257107---Book_File-Web_PDF_9798400691218_486731.pdf"=>file:resolve-path($base)
let $doc:=pdfbox:open($src)
let $labels:= pdfbox:pageLabels($doc)
let $pdfs:=doc("pdfs\chunks-docbook.xml")/chunks/pdf
for $pdf in $pdfs
let $range:=$pdf/@pages/tokenize(.,"")
let $start:=$range[1]
let $end:=if(count($range) eq 1) then $range[1] else $range[2]
let $startIndex:=index-of($labels,$start)
let $endIndex:=index-of($labels,$end)
return if(exists($startIndex) and exists($endIndex))
then $pdf/@pages || " " || $startIndex || ":" || $endIndex
(: pdfbox:extract($doc,$startIndex,$endIndex,file:resolve-path($pdf/@fileref,$base)) :)
else $pdf/@pages

View file

@ -1,8 +0,0 @@
declare variable $samples:= map{
"climate": "data\drop-01d\set\2-6-1\A5579C_1\271989---Book_File-Web_PDF_9798400627484_486728.pdf",
"women": "data\drop-01d\set\2-6-1\A6229C_1\257334---Book_File-Web_PDF_9798216172628_486742.pdf",
"genocide": "data\drop1-pdf\GR2967-TRD\272791---Book_File-Web_PDF_9798400640216_486366.pdf",
"world": "data\drop-01c\gpg-book\2-6\A3506C-TRD\256186---Book_File-Web_PDF_9798216038955_486148.pdf"
};
declare variable $base:= "C:\Users\mrwhe\git\bloomsbury\content-architecture\xquery\ABC-CLIO\data";
42

View file

@ -1,20 +0,0 @@
(:~ describe book page numbering :)
import module namespace pdfbox="urn:expkg-zone58:pdfbox3" ;
import module namespace bookpages="urn:bookpages" at "../lib/bookpages.xqm";
import module namespace pdfscrape="urn:pdfscrape" at "../lib/pdfscrape.xqm";
declare variable $base:="C:\Users\mrwhe\Desktop\1e\";
declare variable $tests:=map{
"simple":"20#C,R,7D",
"set\2-6-2\A5267C": "1037#C,r,28D,520r:V2,526D@493",
"gpg-book\2-3\A3581C-TRD": "848#C,r:Vol1:,28D,400r:Vol2:,438D@401"
};
let $pdf:=pdfbox:open("C:\Users\mrwhe\Desktop\1e\set\2-6-2\A5267C\257273---Book_File-Web_PDF_9798400612572_486638.pdf")
let $l:=pdfbox:getPageLabels($pdf)
let $index:=bookpages:expand($tests?"set\2-6-2\A5267C")
return pdfscrape:score($l,pdfscrape:page-report($pdf))

View file

@ -1,23 +0,0 @@
(: PDFBOX experiments
:)
import module namespace pdfbox="urn:expkg-zone58:pdfbox3" at "../lib/pdfbox3.xqm";
declare variable $samples:= map{
"climate": "data\drop-01d\set\2-6-1\A5579C_1\271989---Book_File-Web_PDF_9798400627484_486728.pdf",
"women": "data\drop-01d\set\2-6-1\A6229C_1\257334---Book_File-Web_PDF_9798216172628_486742.pdf",
"genocide": "data\drop1-pdf\GR2967-TRD\272791---Book_File-Web_PDF_9798400640216_486366.pdf",
"world": "data\drop-01c\gpg-book\2-6\A3506C-TRD\256186---Book_File-Web_PDF_9798216038955_486148.pdf"
};
declare variable $base:= "C:\Users\mrwhe\git\bloomsbury\content-architecture\xquery\ABC-CLIO\data";
(:~ resolve :)
declare variable $PDF:=
$samples?world=>file:resolve-path($base)
(: "C:\Users\mrwhe\git\expkg-zone58\pdfbox\samples.pdf\icelandic-dictionary.pdf" :)
;
pdfbox:report($PDF)