Created
November 30, 2019 02:32
-
-
Save rjkat/9df5d6deec686387563409fe59ecbbb3 to your computer and use it in GitHub Desktop.
remove duplicate pages from a PDF
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
# dedup.jl | |
# wrapper around Apache PDFBox (https://pdfbox.apache.org/) | |
# for removing duplicate pages from a PDF | |
# only tested on macOS | |
JAR = "pdfbox-app-2.0.17.jar" | |
pdfbox(args...) = run(`java -jar $JAR $args`) | |
numpages(pdf) = parse(Int, read( | |
`mdls -name kMDItemNumberOfPages -raw $pdf`, | |
String | |
)) | |
function extractpage(infile, page) | |
f = tempname() | |
pdfbox("ExtractText", | |
"-startPage", page, | |
"-endPage", page, | |
infile, f | |
) | |
readlines(f) | |
end | |
abstract type AbstractDupTracker end | |
Base.@kwdef mutable struct SlideTracker <: AbstractDupTracker | |
curslide::Int = 1 | |
end | |
function prevdup(context::SlideTracker, prevlines, lines) | |
m = match(r"^(\d+)\s*/\s*(\d+)", lines[end]) | |
if !isnothing(m) | |
slide = parse(Int, m.captures[1]) | |
dup = slide == context.curslide | |
if !dup | |
context.curslide = slide | |
end | |
return dup | |
end | |
return false | |
end | |
function uniquepages(pdf, tracker::AbstractDupTracker) | |
n = numpages(pdf) | |
unique = Int[] | |
if n < 1 | |
return unique | |
end | |
prevlines = extractpage(pdf, 1) | |
for i = 2:n | |
lines = extractpage(pdf, i) | |
if !prevdup(tracker, prevlines, lines) | |
push!(unique, i - 1) | |
end | |
prevlines = lines | |
end | |
push!(unique, n) | |
unique | |
end | |
defaultoutname(inpdf) = joinpath(dirname(inpdf), splitext(basename(inpdf))[1] * "-unique.pdf") | |
function selectpages(inpdf, pages, outpdf=defaultoutname(inpdf)) | |
filename = basename(inpdf) | |
dir = mktempdir() | |
tmppdf = joinpath(dir, filename) | |
cp(inpdf, tmppdf) | |
for page in pages | |
pdfbox("PDFSplit", tmppdf, "-startPage", page, "-endPage", page, "-outputPrefix", joinpath(dir, string(page))) | |
end | |
pdfs = [joinpath(dir, "$page-1.pdf") for page in pages] | |
pdfbox("PDFMerger", pdfs..., outpdf) | |
outpdf | |
end | |
function dedup(inpdf, outpdf=defaultoutname(inpdf), tracker=SlideTracker()) | |
pages = uniquepages(inpdf, tracker) | |
selectpages(inpdf, pages, outpdf) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment