def merge_metadata(src,dst):
'''
Sets the metadata of dst to the metadata of src pdf files.
.. note:: pdftk is used for extracting and updating the metadata.
'''
tmp=NamedTemporaryFile(dir=".",delete=False)
srcm=_(["pdftk",src,"dump_data"],stdout=PIPE)
dstm=_(["pdftk",dst,"update_info","-","output",tmp.name],stdin=srcm.stdout)
srcm.stdout.close() # for pipe to work correctly (SIGPIPE)
dstm.communicate()
# move temporary file to the actual file
os.rename(tmp.name, dst)
def merge_metadata(src, dst):
'''
Sets the metadata of dst to the metadata of src pdf files.
.. note:: pdftk is used for extracting and updating the metadata.
'''
tmp = NamedTemporaryFile(dir=".", delete=False)
srcm = _(["pdftk", src, "dump_data"], stdout=PIPE)
dstm = _(["pdftk", dst, "update_info", "-", "output", tmp.name],
stdin=srcm.stdout)
srcm.stdout.close() # for pipe to work correctly (SIGPIPE)
dstm.communicate()
# move temporary file to the actual file
os.rename(tmp.name, dst)
def call_tesseract(file):
'''
Calls tesseract to generate the hocr of a page. The output pdf
file name is the image filename plus ".pdf" extension.
:param file: the path to the page image
'''
args=["tesseract",file,file,"hocr"]
p=_(args); p.communicate()
def call_tesseract(file):
'''
Calls tesseract to generate the hocr of a page. The output pdf
file name is the image filename plus ".pdf" extension.
:param file: the path to the page image
'''
args = ["tesseract", file, file, "hocr"]
p = _(args)
p.communicate()
def call_hocr(pdffile,imagefile,hocrfile):
'''
calls hocr2pdf and generates a pdf from a single page pdf file.
:param pdffile: the output pdf filename
:param imagefile: the input image filename
:param hocrfile: the input hocr filename
'''
args=["hocr2pdf","-i",imagefile,"-o",pdffile]
p=_(args,stdin=PIPE)
with open(hocrfile,"r") as hocr:
p.communicate(input=hocr.read())
def call_hocr(pdffile, imagefile, hocrfile):
'''
calls hocr2pdf and generates a pdf from a single page pdf file.
:param pdffile: the output pdf filename
:param imagefile: the input image filename
:param hocrfile: the input hocr filename
'''
args = ["hocr2pdf", "-i", imagefile, "-o", pdffile]
p = _(args, stdin=PIPE)
with open(hocrfile, "r") as hocr:
p.communicate(input=hocr.read())
def merge_pdfs(pdflist,output):
'''
Merge the pdf files into a single one. The page order is the
same as the order of the list.
.. note:: ghostscript with pdfwrite is used for this process.
:param pdflist: list of pdf filenames
:param output: the name of the output pdf
'''
args=["gs","-dBATCH","-dNOPAUSE","-q","-sDEVICE=pdfwrite",
"-dNumRenderingThreads=%d"%THREADS,
"-sOutputFile="+output,
"-c","30000000 setvmthreshold",
"-f"]+pdflist
p=_(args); p.communicate()
def merge_pdfs(pdflist, output):
'''
Merge the pdf files into a single one. The page order is the
same as the order of the list.
.. note:: ghostscript with pdfwrite is used for this process.
:param pdflist: list of pdf filenames
:param output: the name of the output pdf
'''
args = [
"gs", "-dBATCH", "-dNOPAUSE", "-q", "-sDEVICE=pdfwrite",
"-dNumRenderingThreads=%d" % THREADS, "-sOutputFile=" + output, "-c",
"30000000 setvmthreshold", "-f"
] + pdflist
p = _(args)
p.communicate()
def create_tiffs(pdf):
'''
Split pdf into images for each page of the pdf. The images are
output in tiff format and named "image<page-number>.tiff".
.. note:: The images are generated in the current directory.
.. note:: ghostscript with tiffg4 device is used.
:param pdf: the path to the pdf file.
'''
args=["gs","-dNOPAUSE","-sDEVICE=tiffg4",
"-dNumRenderingThreads=%d"%THREADS,
"-dFirstPage=1",
"-sOutputFile=image%d.tiff",
"-r%d"%RESOLUTION,"-q",
"-c","30000000 setvmthreshold",
"-f",pdf,"-c","quit"]
p=_(args); p.communicate()
def create_tiffs(pdf):
'''
Split pdf into images for each page of the pdf. The images are
output in tiff format and named "image<page-number>.tiff".
.. note:: The images are generated in the current directory.
.. note:: ghostscript with tiffg4 device is used.
:param pdf: the path to the pdf file.
'''
args = [
"gs", "-dNOPAUSE", "-sDEVICE=tiffg4",
"-dNumRenderingThreads=%d" % THREADS, "-dFirstPage=1",
"-sOutputFile=image%d.tiff",
"-r%d" % RESOLUTION, "-q", "-c", "30000000 setvmthreshold", "-f", pdf,
"-c", "quit"
]
p = _(args)
p.communicate()
def which(exe):
t = _p(_(["where.exe", exe],
capture_output=True).stdout.decode().strip()).resolve()
if t.is_file():
return str(t)