def convertAnnotatedPDF(fname, refNrPath, origPDF):
"""
Converts a PDF and it's annotations into one PDF.
"""
#tempdir is where I will save in between files
try:
os.mkdir("tempDir")
except:
pass
print(fname + " is being exported.")
# get info on origin pdf
input1 = PdfFileReader(open(origPDF, "rb"))
npages = input1.getNumPages()
pdfsize = input1.getPage(0).mediaBox
pdfx = int(pdfsize[2])
pdfy = int(pdfsize[3])
# rM will not create a file when the page is empty so this is a
# placeholde empty file to use.
rm2svg(emptyRm,
"tempDir/emptyrm.svg",
coloured_annotations=True,
x_width=pdfx,
y_width=pdfy)
# find what the page hashes are
content = json.loads(open(refNrPath + ".content").read())
# convert all pages
pdflist = []
for pg, pg_hash in enumerate(content['pages']):
# print(pg)
rmpath = refNrPath + "/" + pg_hash + ".rm"
if os.path.isfile(rmpath):
rm2svg(rmpath,
"tempDir/temprm" + str(pg) + ".svg",
coloured_annotations=False,
x_width=pdfx,
y_width=pdfy)
svg_path = "tempDir/temprm" + str(pg) + ".svg"
else:
svg_path = "tempDir/emptyrm.svg"
convertSvg2PdfCmd = "".join([
"rsvg-convert -f pdf -o ", "tempDir/temppdf" + str(pg), ".pdf ",
svg_path
])
os.system(convertSvg2PdfCmd)
pdflist.append("tempDir/temppdf" + str(pg) + ".pdf")
# merge the annotated pages
merged_rm = "tempDir/merged_rm.pdf"
os.system("convert " + (" ").join(pdflist) + " " + merged_rm)
# stamp extracted annotations onto original with pdftk
stampCmd = "".join([
"pdftk ", origPDF, " multistamp ", merged_rm, " output ", origPDF[:-4],
"_annot.pdf"
])
os.system(stampCmd)
# Remove temporary files
shutil.rmtree("tempDir", ignore_errors=False, onerror=None)
return True
def convertNotebook(fname, refNrPath):
"""
Converts Notebook to a PDF by taking the annotations and the template
background for that notebook.
"""
#tempdir is where I will save in between files
try:
os.mkdir('tempDir')
except:
pass
# get list of backgrounds
with open(refNrPath + ".pagedata") as file:
backgrounds = [line.strip() for line in file]
bg_pg = 0
bglist = []
for bg in backgrounds:
convertSvg2PdfCmd = "".join(["rsvg-convert -f pdf -o ", "tempDir/bg_"\
+ str(bg_pg) + ".pdf ", str(bgPath)\
+ bg.replace(" ", "\ ") + ".svg"])
os.system(convertSvg2PdfCmd)
bglist.append("tempDir/bg_" + str(bg_pg) + ".pdf ")
bg_pg += 1
merged_bg = "tempDir/merged_bg.pdf"
os.system("convert " + (" ").join(bglist) + " " + merged_bg)
# get info from the pdf we just made
input1 = PdfFileReader(open(merged_bg, 'rb'))
pdfsize = input1.getPage(0).mediaBox
# find out the page hashes
content = json.loads(open(refNrPath + ".content").read())
# Now convert all Pages
pdflist = []
for pg, pg_hash in enumerate(content['pages']):
rmpath = refNrPath + "/" + pg_hash + ".rm"
# skip page if it doesnt extist anymore. This is fine in notebooks
# because nobody cares about the rM numbering.
try:
rm2svg(rmpath,
"tempDir/temprm" + str(pg) + ".svg",
coloured_annotations=True)
convertSvg2PdfCmd = \
"".join(["rsvg-convert -f pdf -o ", "tempDir/temppdf" + \
str(pg), ".pdf ", "tempDir/temprm" + str(pg) + ".svg"])
os.system(convertSvg2PdfCmd)
pdflist.append("tempDir/temppdf" + str(pg) + ".pdf")
except FileNotFoundError:
continue
# merge all annotation pages
merged_rm = "tempDir/merged_rm.pdf"
os.system("convert " + (" ").join(pdflist) + " " + merged_rm)
# combine with background
stampCmd = "".join(["pdftk ", merged_bg, " multistamp ", merged_rm, \
" output " + syncDirectory + "/Notes/" + fname + ".pdf"])
os.system(stampCmd)
# Delete temp directory
shutil.rmtree("tempDir", ignore_errors=False, onerror=None)
return True
def convertAnnotatedPDF(fname, refNrPath, origPDF, verbose=False):
"""
Converts a PDF and it's annotations into one PDF.
"""
#tempdir is where I will save in between files
try:
os.mkdir("tempDir")
except:
pass
print(fname + " is being exported.")
# get info on origin pdf
try:
input1 = pikepdf.Pdf.open(origPDF)
#input1 = PdfFileReader(open(origPDF, "rb"))
except:
warnings.warn("could not read " + origPDF)
return False
npages = len(input1.pages)
pdfsize = input1.pages[0].trimbox
pdfx = int(pdfsize[2])
pdfy = int(pdfsize[3])
if verbose:
print(f"the pdf has size {pdfx}x{pdfy}")
# rM will not create a file when the page is empty so this is a
# placeholde empty file to use.
rm2svg(emptyRm, "tempDir/emptyrm.svg", coloured_annotations=True)
ratio_rm = 1872 / 1404
ratio_pdf = pdfy / pdfx
# rotate landscape pdfs
landscape = False
if ratio_pdf < 1:
if verbose:
print(f"its landscape format {ratio_pdf}")
landscape = True
if ratio_pdf != ratio_rm:
pdf_obj = resize_pages(origPDF, landscape, verbose=verbose)
pdf_obj.save("tempdir/resized.pdf") # saves as "resizedPDF"
resizedPDF = "tempdir/resized.pdf"
#warnings.warn("The PDF you are annotating has an unexpected size. Annotations may be misaligned.")
# find what the page hashes are
content = json.loads(open(refNrPath + ".content").read())
# convert all pages
pdflist = []
for pg, pg_hash in enumerate(content['pages']):
if verbose:
print(f"converting page {pg}")
rmpath = refNrPath + "/" + pg_hash + ".rm"
if os.path.isfile(rmpath):
rm2svg(rmpath,
"tempDir/temprm" + str(pg) + ".svg",
coloured_annotations=False)
svg_path = "tempDir/temprm" + str(pg) + ".svg"
else:
svg_path = "tempDir/emptyrm.svg"
convertSvg2PdfCmd = "".join([
"rsvg-convert -f pdf -a -o ", "tempDir/temppdf" + str(pg), ".pdf ",
svg_path
])
os.system(convertSvg2PdfCmd)
pdflist.append("tempDir/temppdf" + str(pg) + ".pdf")
# merging at high quality gets sooo slow, so we decrease quality for big files
density_pdf = 200
quality_pdf = 80
if pg > 80:
density_pdf = 100
quality_pdf = 50
# merge the annotated pages
merged_rm = "tempDir/merged_rm.pdf"
mergeCmd = f"convert -density {density_pdf}x{density_pdf} -quality {quality_pdf} " + (
" ").join(pdflist) + " " + merged_rm
if verbose:
print(f"Doing Merge: {mergeCmd}")
#print(mergeCmd)
os.system(mergeCmd)
# stamp extracted annotations onto original with pdftk
stampCmd = "".join([
"pdftk ", resizedPDF, " multistamp ", merged_rm, " output ",
origPDF[:-4], "_annot.pdf"
])
if verbose:
print(f"Doing Stamp: {stampCmd}")
os.system(stampCmd)
# Remove temporary files
shutil.rmtree("tempDir", ignore_errors=False, onerror=None)
return True
def convertAnnotatedPDF(fname, refNrPath, origPDF):
"""
Converts a PDF and it's annotations into one PDF.
"""
#tempdir is where I will save in between files
try:
os.mkdir("tempDir")
except:
pass
print(fname+" is being exported.")
# get info on origin pdf
try:
input1 = PdfFileReader(open(origPDF, "rb"))
except:
warnings.warn("could not read " + origPDF)
return False
npages = input1.getNumPages()
pdfsize = input1.getPage(0).mediaBox
pdfx = int(pdfsize[2])
pdfy = int(pdfsize[3])
# rM will not create a file when the page is empty so this is a
# placeholde empty file to use.
rm2svg(emptyRm, "tempDir/emptyrm.svg", coloured_annotations=True)
ratio_rm = 1872 / 1404
ratio_pdf = pdfy / pdfx
# rotate landscape pdfs
landscape = False
if ratio_pdf < 1:
landscape = True
os.system("pdftk " + origPDF + " cat 1-endwest output tempdir/rotated.pdf")
pdfx = int(pdfsize[3])
pdfy = int(pdfsize[2])
ratio_pdf = pdfy / pdfx
resizedPDF = "tempdir/rotated.pdf"
else:
resizedPDF = origPDF
if ratio_pdf < ratio_rm:
keep_side = "x"
change_side = "y"
else:
keep_side = "y"
change_side = "x"
size = {"x" : pdfx, "y" : pdfy}
keep_side_is = size[keep_side]
change_side_is = size[change_side]
change_side_should = keep_side_is * ratio_rm if keep_side_is < change_side_is else keep_side_is / ratio_rm
yoffset = change_side_should - change_side_is if change_side == "y" else 0
#print(size, ratio_rm, ratio_pdf, keep_side, change_side, keep_side_is, change_side_is, change_side_should, yoffset)
output_size = [keep_side_is, change_side_should] if change_side == "y" else [change_side_should, keep_side_is]
rszCmd = "gs -o tempDir/resized_org.pdf -sDEVICE=pdfwrite -g"+str(int(output_size[0]))+"0x"+str(int(output_size[1]))+"0 -c '<</PageOffset [0 " + str(int(yoffset)) + "]>> setpagedevice' -f " + resizedPDF
#print(rszCmd)
os.system(rszCmd)
if landscape:
os.system("pdftk tempDir/resized_org.pdf cat 1-endnorth output tempdir/resized_org2.pdf")
resizedPDF = "tempDir/resized_org2.pdf"
else:
resizedPDF = "tempDir/resized_org.pdf"
# find what the page hashes are
content = json.loads(open(refNrPath + ".content").read())
# convert all pages
pdflist = []
for pg, pg_hash in enumerate(content['pages']):
# print(pg)
rmpath = refNrPath + "/" + pg_hash + ".rm"
if os.path.isfile(rmpath):
rm2svg(rmpath, "tempDir/temprm" + str(pg) + ".svg", coloured_annotations=False)
svg_path = "tempDir/temprm" + str(pg) + ".svg"
else:
svg_path = "tempDir/emptyrm.svg"
convertSvg2PdfCmd = "".join(["rsvg-convert -f pdf -a -o ", "tempDir/temppdf" + str(pg), ".pdf ", svg_path])
os.system(convertSvg2PdfCmd)
pdflist.append("tempDir/temppdf"+str(pg)+".pdf")
# merge the annotated pages
merged_rm = "tempDir/merged_rm.pdf"
mergeCmd = "convert -density 200x200 -quality 80 " + (" ").join(pdflist) + " " + merged_rm
#print(mergeCmd)
os.system(mergeCmd)
# stamp extracted annotations onto original with pdftk
stampCmd = "".join(["pdftk ", resizedPDF, " multistamp ", merged_rm, " output ", origPDF[:-4], "_annot.pdf"])
os.system(stampCmd)
# Remove temporary files
shutil.rmtree("tempDir", ignore_errors=False, onerror=None)
return True