menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor image file triage

Browse Source
This commit is contained in:
James R. Barlow
2016-07-31 01:47:57 -07:00
parent 48213c9c3f
commit 968e1546f0
1 changed files with 50 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ocrmypdf/main.py
+50 -42
View File
@@ -386,6 +386,54 @@ def cleanup_working_files(*args):
shutil.rmtree(work_folder)
def triage_image_file(input_file, output_file, log):
try:
log.info("Input file is not a PDF, checking if it is an image...")
im = Image.open(input_file)
except EnvironmentError as e:
log.error(e)
sys.exit(ExitCode.input_file)
return
else:
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.oversample:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --oversample.")
sys.exit(ExitCode.input_file)
elif not options.oversample:
log.info("Image size: (%d, %d)" % im.size)
log.error(
"Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --oversample.")
sys.exit(ExitCode.input_file)
finally:
im.close()
try:
log.info("Image seems valid. Try converting to PDF...")
layout_fun = img2pdf.default_layout_fun
if options.oversample:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.oversample, options.oversample))
with open(output_file, 'wb') as outf:
img2pdf.convert(
input_file,
layout_fun=layout_fun,
with_pdfrw=False,
outputstream=outf)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
sys.exit(ExitCode.input_file)
@transform(
input=options.input_file,
filter=formatter('(?i)'),
@@ -401,52 +449,12 @@ def triage(
if signature == b'%PDF':
re_symlink(input_file, output_file)
return
# We opened the file, but it's not a PDF
f.seek(0)
log.info("Input file is not a PDF, checking if it is an image...")
im = Image.open(f)
f = None # Image.load() closes the file handle
log.info("Input file is an image")
if 'dpi' in im.info:
if im.info['dpi'] <= (96, 96) and not options.oversample:
log.info("Image size: (%d, %d)" % im.size)
log.info("Image resolution: (%d, %d)" % im.info['dpi'])
log.error(
"Input file is an image, but the resolution (DPI) is "
"not credible. Estimate the resolution at which the "
"image was scanned and specify it using --oversample.")
sys.exit(ExitCode.input_file)
elif not options.oversample:
log.info("Image size: (%d, %d)" % im.size)
log.error(
"Input file is an image, but has no resolution (DPI) "
"in its metadata. Estimate the resolution at which "
"image was scanned and specify it using --oversample.")
sys.exit(ExitCode.input_file)
im.close()
log.info("Image seems valid. Try converting to PDF...")
layout_fun = None
if options.oversample:
layout_fun = img2pdf.get_fixed_dpi_layout_fun(
(options.oversample, options.oversample))
with open(output_file, 'wb') as outf:
img2pdf.convert(
input_file,
layout_fun=layout_fun,
with_pdfrw=False,
outputstream=outf)
log.info("Successfully converted to PDF, processing...")
except img2pdf.ImageOpenError as e:
log.error(e)
sys.exit(ExitCode.input_file)
except EnvironmentError as e:
log.error(e)
sys.exit(ExitCode.input_file)
triage_image_file(input_file, output_file, log)
@transform(
input=triage,