expkg-zone58/pdfbox
1
0
Fork 0
Code Activity Actions

[snap]

Browse source
This commit is contained in:
Andy Bunce 2024-04-08 23:03:36 +01:00
parent 2b131ee71a
commit bd5b7cf006
14 changed files with 249 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/pdfbox.xqbk
View file

@ -1 +1 @@
{"cells":[{"kind":1,"language":"markdown","value":"# PDFBox3 \r\nA BaseX 10+ interface to Apache PDFBox® library version 3 \r\n## Apache PDFBox® - A Java PDF Library\r\n\r\nThe Apache PDFBox® library is an open source Java tool for working with PDF documents. This project allows creation of new PDF documents, manipulation of existing documents and the ability to extract content from documents. Apache PDFBox also includes several command-line utilities. Apache PDFBox is published under the Apache License v2.0.\r\nhttps://pdfbox.apache.org/"},{"kind":1,"language":"markdown","value":"It comes with the useful PDF debug tool `java -jar debugger-app-3.0.1.jar`"},{"kind":1,"language":"markdown","value":"## Set up XQuery context for following code..."},{"kind":2,"language":"xquery","value":"(:<:)(: XQuery Context :)\r\nimport module namespace pdfbox = \"urn:expkg-zone58:pdfbox3\" at \"../src/lib/pdfbox3.xqm\";\r\nimport module namespace bookpages = 'urn:bookpages' at \"../src/lib/bookpages.xqm\";\r\nimport module namespace config = 'urn:abc-clio:config' at 'C:\\Users\\mrwhe\\git\\bloomsbury\\content-architecture\\xquery\\ABC-CLIO/lib/abc-config.xqm';\r\n\r\ndeclare variable $samples:= map{\r\n \"climate\": \"drop-01d\\set\\2-6-1\\A5579C_1\\271989---Book_File-Web_PDF_9798400627484_486728.pdf\",\r\n \"women\": \"drop-01d\\set\\2-6-1\\A6229C_1\\257334---Book_File-Web_PDF_9798216172628_486742.pdf\",\r\n \"genocide\": \"drop1-pdf\\GR2967-TRD\\272791---Book_File-Web_PDF_9798400640216_486366.pdf\",\r\n \"world\": \"drop-01c\\gpg-book\\2-6\\A3506C-TRD\\256186---Book_File-Web_PDF_9798216038955_486148.pdf\"\r\n};\r\ndeclare variable $PDF:= (: $samples?women=>file:resolve-path($config:data) :)\r\n\"C:\\Users\\mrwhe\\git\\bloomsbury\\content-architecture\\xquery\\ABC-CLIO\\data\\drop-01e\\set\\2-6-1\\A5690C_1\\257107---Book_File-Web_PDF_9798400691218_486731.pdf\";"},{"kind":1,"language":"markdown","value":"# Version"},{"kind":1,"language":"markdown","value":" ## pdfbox version"},{"kind":2,"language":"xquery","value":"pdfbox:version()"},{"kind":1,"language":"markdown","value":"PDF specification version used by document"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:pdfVersion()"},{"kind":1,"language":"markdown","value":"# Page count for PDF"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:page-count()"},{"kind":1,"language":"markdown","value":"## save range to new pdf"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:extract(2,12,\"c:\\tmp\\a.pdf\")"},{"kind":1,"language":"markdown","value":"## Outline / bookmarks"},{"kind":1,"language":"markdown","value":"### sequence of maps"},{"kind":2,"language":"xquery","value":"\r\npdfbox:open($PDF)=>pdfbox:outline()"},{"kind":1,"language":"markdown","value":"XML"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:outline()=>pdfbox:outline-xml()"},{"kind":1,"language":"markdown","value":"## Page labels"},{"kind":2,"language":"xquery","value":"\r\npdfbox:open($PDF)=>pdfbox:getPageLabels()"},{"kind":1,"language":"markdown","value":"# getText from page index"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pdfbox:getText($doc,56)"},{"kind":1,"language":"markdown","value":"## PageNo text analysis"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pagenos:page-report($doc)\r\n"},{"kind":1,"language":"markdown","value":"# Inverted pageno map"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pagenos:page-report($doc)=>pagenos:inverted-map()"},{"kind":1,"language":"markdown","value":"## report"},{"kind":2,"language":"xquery","value":"declare variable $a:=file:resolve-path(\"../data/1e/\",file:base-dir());\r\n\r\nfor $f in file:list($a,true(),\"*.pdf\") \r\nwhere not(contains($f,\"outputs\"))\r\nlet $doc:=pdfbox:open(file:resolve-path($f,$a))\r\n(: let $outline:=pdfbox:outline($doc) :)\r\nlet $count:=pdfbox:page-count($doc)\r\norder by $count \r\nreturn ``[`{$f}`: `{ $count }`]``"}]}
{"cells":[{"kind":1,"language":"markdown","value":"# PDFBox3 \r\nA BaseX 10+ interface to Apache PDFBox® library version 3 \r\n## Apache PDFBox® - A Java PDF Library\r\n\r\nThe Apache PDFBox® library is an open source Java tool for working with PDF documents. This project allows creation of new PDF documents, manipulation of existing documents and the ability to extract content from documents. Apache PDFBox also includes several command-line utilities. Apache PDFBox is published under the Apache License v2.0.\r\nhttps://pdfbox.apache.org/"},{"kind":1,"language":"markdown","value":"It comes with the useful PDF debug tool `java -jar debugger-app-3.0.1.jar`"},{"kind":1,"language":"markdown","value":"## Set up XQuery context for following code..."},{"kind":2,"language":"xquery","value":"(:<:)(: XQuery Context :)\r\nimport module namespace pdfbox = \"urn:expkg-zone58:pdfbox3\" at \"../src/lib/pdfbox3.xqm\";\r\nimport module namespace bookpages = 'urn:bookpages' at \"../src/lib/bookpages.xqm\";\r\nimport module namespace config = 'urn:abc-clio:config' at 'C:\\Users\\mrwhe\\git\\bloomsbury\\content-architecture\\xquery\\ABC-CLIO/lib/abc-config.xqm';\r\n\r\ndeclare variable $samples:= map{\r\n \"climate\": \"drop-01d\\set\\2-6-1\\A5579C_1\\271989---Book_File-Web_PDF_9798400627484_486728.pdf\",\r\n \"women\": \"drop-01d\\set\\2-6-1\\A6229C_1\\257334---Book_File-Web_PDF_9798216172628_486742.pdf\",\r\n \"genocide\": \"drop1-pdf\\GR2967-TRD\\272791---Book_File-Web_PDF_9798400640216_486366.pdf\",\r\n \"world\": \"drop-01c\\gpg-book\\2-6\\A3506C-TRD\\256186---Book_File-Web_PDF_9798216038955_486148.pdf\"\r\n};\r\ndeclare variable $PDF:= (: $samples?women=>file:resolve-path($config:data) :)\r\n\"C:\\Users\\mrwhe\\git\\bloomsbury\\content-architecture\\xquery\\ABC-CLIO\\data\\drop-01e\\set\\2-6-1\\A5690C_1\\257107---Book_File-Web_PDF_9798400691218_486731.pdf\";"},{"kind":1,"language":"markdown","value":"# Version"},{"kind":1,"language":"markdown","value":" ## pdfbox version"},{"kind":2,"language":"xquery","value":"pdfbox:version()"},{"kind":1,"language":"markdown","value":"PDF specification version used by document"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:pdfVersion()"},{"kind":1,"language":"markdown","value":"# Page count for PDF"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:page-count()"},{"kind":1,"language":"markdown","value":"## save range to new pdf"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:extract(2,12,\"c:\\tmp\\a.pdf\")"},{"kind":1,"language":"markdown","value":"## Outline / bookmarks"},{"kind":1,"language":"markdown","value":"### sequence of maps"},{"kind":2,"language":"xquery","value":"\r\npdfbox:open($PDF)=>pdfbox:outline()"},{"kind":1,"language":"markdown","value":"XML"},{"kind":2,"language":"xquery","value":"pdfbox:open($PDF)=>pdfbox:outline()=>pdfbox:outline-xml()"},{"kind":1,"language":"markdown","value":"## Page labels"},{"kind":2,"language":"xquery","value":"\r\npdfbox:open($PDF)=>pdfbox:pageLabels()"},{"kind":1,"language":"markdown","value":"# getText from page index"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pdfbox:getText($doc,56)"},{"kind":1,"language":"markdown","value":"## PageNo text analysis"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pagenos:page-report($doc)\r\n"},{"kind":1,"language":"markdown","value":"# Inverted pageno map"},{"kind":2,"language":"xquery","value":"let $doc:=pdfbox:open($PDF)\r\nreturn pagenos:page-report($doc)=>pagenos:inverted-map()"},{"kind":1,"language":"markdown","value":"## report"},{"kind":2,"language":"xquery","value":"declare variable $a:=file:resolve-path(\"../data/1e/\",file:base-dir());\r\n\r\nfor $f in file:list($a,true(),\"*.pdf\") \r\nwhere not(contains($f,\"outputs\"))\r\nlet $doc:=pdfbox:open(file:resolve-path($f,$a))\r\n(: let $outline:=pdfbox:outline($doc) :)\r\nlet $count:=pdfbox:page-count($doc)\r\norder by $count \r\nreturn ``[`{$f}`: `{ $count }`]``"}]}