Created
November 29, 2013 17:59
-
-
Save peaeater/7709591 to your computer and use it in GitHub Desktop.
Produce a canvas structure XML (which djvulibre calls 'hidden text') file per page from a DJVU file. Output name includes total page count of input file, and page number of current page. Requires djvutoxml => http://djvu.sourceforge.net/doc/man/djvuxml.html
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# extract hidden text xml per page from djvu | |
# requires djvulibre | |
param( | |
[Parameter(Mandatory=$true,ValueFromPipeline=$true,Position=0)] | |
[string]$in | |
) | |
process | |
{ | |
$basePath = split-path $script:myinvocation.mycommand.path | |
$file = new-object System.IO.FileInfo([System.IO.Path]::Combine($basePath, $in)) | |
$input = ('"{0}"' -f $file.FullName) | |
write-host $input | |
$pagecount = & djvused -e 'n' $input | |
for ($i = 1; $i -le $pagecount; $i++) { | |
$output = ('"{0}\{1}_t{2}_{3}.xml"' -f $file.DirectoryName, $file.BaseName, $pagecount, $i) | |
$args = "--with-text --page $i $input $output" | |
write-host $args | |
start-process djvutoxml $args -NoNewWindow -wait | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment