def call_convert(input_file, output_file, **kwargs):
if ".pdf" in input_file:
raise ParseError("Does not compute.")
else:
run_convert(input_file=input_file,
output_file=output_file,
**kwargs)
def get_thumbnail(self, document_path, mime_type):
self.log("info",
f"[TIKA_THUMB] Generating thumbnail for{document_path}")
archive_path = self.archive_path
out_path = os.path.join(self.tempdir, "convert.png")
# Run convert to get a decent thumbnail
try:
run_convert(
density=300,
scale="500x5000>",
alpha="remove",
strip=True,
trim=False,
input_file="{}[0]".format(archive_path),
output_file=out_path,
logging_group=self.logging_group,
)
except ParseError:
# if convert fails, fall back to extracting
# the first PDF page as a PNG using Ghostscript
self.log(
"warning",
"Thumbnail generation with ImageMagick failed, falling back "
"to ghostscript. Check your /etc/ImageMagick-x/policy.xml!",
)
gs_out_path = os.path.join(self.tempdir, "gs_out.png")
cmd = [
settings.GS_BINARY,
"-q",
"-sDEVICE=pngalpha",
"-o",
gs_out_path,
archive_path,
]
if not subprocess.Popen(cmd).wait() == 0:
raise ParseError("Thumbnail (gs) failed at {}".format(cmd))
# then run convert on the output from gs
run_convert(
density=300,
scale="500x5000>",
alpha="remove",
strip=True,
trim=False,
input_file=gs_out_path,
output_file=out_path,
logging_group=self.logging_group,
)
return out_path
def get_thumbnail(self, document_path, mime_type):
"""
The thumbnail of a PDF is just a 500px wide image of the first page.
"""
out_path = os.path.join(self.tempdir, "convert.png")
# Run convert to get a decent thumbnail
try:
run_convert(density=300,
scale="500x5000>",
alpha="remove",
strip=True,
trim=False,
auto_orient=True,
input_file="{}[0]".format(document_path),
output_file=out_path,
logging_group=self.logging_group)
except ParseError:
# if convert fails, fall back to extracting
# the first PDF page as a PNG using Ghostscript
self.log(
'warning',
"Thumbnail generation with ImageMagick failed, falling back "
"to ghostscript. Check your /etc/ImageMagick-x/policy.xml!")
gs_out_path = os.path.join(self.tempdir, "gs_out.png")
cmd = [
settings.GS_BINARY, "-q", "-sDEVICE=pngalpha", "-o",
gs_out_path, document_path
]
if not subprocess.Popen(cmd).wait() == 0:
raise ParseError("Thumbnail (gs) failed at {}".format(cmd))
# then run convert on the output from gs
run_convert(density=300,
scale="500x5000>",
alpha="remove",
strip=True,
trim=False,
auto_orient=True,
input_file=gs_out_path,
output_file=out_path,
logging_group=self.logging_group)
return out_path
def _get_greyscale(self):
"""
Greyscale images are easier for Tesseract to OCR
"""
# Convert PDF to multiple PNMs
input_file = self.document_path
if settings.OCR_PAGES == 1:
input_file += "[0]"
elif settings.OCR_PAGES > 1:
input_file += f"[0-{settings.OCR_PAGES - 1}]"
self.log("debug",
f"Converting document {input_file} into greyscale images")
output_files = os.path.join(self.tempdir, "convert-%04d.pnm")
run_convert(density=settings.CONVERT_DENSITY,
depth="8",
type="grayscale",
input_file=input_file,
output_file=output_files,
logging_group=self.logging_group)
# Get a list of converted images
pnms = []
for f in os.listdir(self.tempdir):
if f.endswith(".pnm"):
pnms.append(os.path.join(self.tempdir, f))
self.log("debug", f"Running unpaper on {len(pnms)} pages...")
# Run unpaper in parallel on converted images
with ThreadPool(processes=settings.THREADS_PER_WORKER) as pool:
pnms = pool.map(run_unpaper, pnms)
return sorted(filter(lambda __: os.path.isfile(__), pnms))
