def subcommand_samples(input_file, state):
"""Generate a list of example files with different threshold values.
:param input_file: The input file.
:type input_file: jfscripts._utils.FilePath
:param state: The state object.
:type state: jfscripts.pdf_compress.State
:return: None
"""
args = state.args
def fix_output_path(output_file):
output_file = str(output_file).replace('_-000', '')
return FilePath(output_file, absolute=True)
if state.input_is_pdf:
page_count = do_pdfinfo_page_count(input_file)
page_number = random.randint(1, page_count)
print('Used page number {} of {} pages to generate a series of images '
'with different threshold values.'.format(
page_number, page_count))
do_pdfimages(input_file, state, page_number)
images = collect_images(state)
input_file = FilePath(images[0], absolute=True)
if args.threshold:
for threshold in range(40, 100, 5):
appendix = '_threshold-{}'.format(threshold)
output_file = input_file.new(extension='tiff',
append=appendix,
del_substring=tmp_identifier)
output_file = str(output_file).replace('_-000', '')
do_magick_convert(input_file,
fix_output_path(output_file),
threshold='{}%'.format(threshold))
if args.quality:
for quality in range(40, 100, 5):
appendix = '_quality-{}'.format(quality)
output_file = input_file.new(extension='pdf',
append=appendix,
del_substring=tmp_identifier)
do_magick_convert(input_file,
fix_output_path(output_file),
color=True,
quality=quality)
if args.blur:
for blur in (1, 2, 3, 4, 5):
appendix = '_blur-{}'.format(blur)
output_file = input_file.new(extension='pdf',
append=appendix,
del_substring=tmp_identifier)
do_magick_convert(input_file,
fix_output_path(output_file),
color=True,
blur=blur,
quality=100)
def test_extraction(self):
pdf = FilePath(tmp_pdf)
subprocess.check_output(['extract-pdftext.py', str(pdf)])
txt = pdf.new(extension='txt')
self.assertTrue(os.path.exists(str(txt)))
self.assertTrue('## Seite' in open(str(txt)).read())
self.assertTrue('Andrew Lloyd Webber' in open(str(txt)).read())
self.assertTrue('-' *
extract_pdftext.line_length in open(str(txt)).read())
def main():
args = get_parser().parse_args()
run.setup(verbose=args.verbose, colorize=args.colorize)
check_dependencies(*dependencies)
pdf = FilePath(args.file, absolute=True)
txt_path = pdf.new(extension='txt')
txt_file = Txt(txt_path)
page_count = get_page_count(pdf)
txt_file.add_line('# ' + pdf.basename)
for i in range(1, page_count + 1):
txt_file.add_line('')
txt_file.add_line('-' * line_length)
txt_file.add_line('')
txt_file.add_line('## Seite ' + str(i))
txt_file.add_line('')
get_text_per_page(pdf, i, txt_file)
def main():
args = get_parser().parse_args()
run.setup(verbose=args.verbose, colorize=args.colorize)
check_dependencies(*dependencies)
main_pdf = FilePath(args.pdf, absolute=True)
image = FilePath(args.image, absolute=True)
if hasattr(args, 'number'):
number = args.number
if image.extension == 'pdf':
insert_pdf = image
else:
identify_pdf = do_pdftk_cat_first_page(main_pdf)
pdf_dimensions = do_magick_identify_dimensions(identify_pdf)
image_dimensions = do_magick_identify_dimensions(image)
insert_pdf = convert_image_to_pdf_page(
image,
image_dimensions['width'],
pdf_dimensions['width'],
pdf_dimensions['x'],
)
info = get_pdf_info(main_pdf)
if args.subcmd_args in ['add', 'ad', 'a']:
if args.after:
number = int(args.after[0])
position = 'after'
elif args.before:
number = int(args.before[0])
position = 'before'
elif args.first:
number = 1
position = 'before'
elif args.last:
number = info['page_count']
position = 'after'
else:
number = info['page_count']
position = 'after'
joined_pdf = assemble_pdf(main_pdf,
insert_pdf,
info['page_count'],
number,
mode='add',
position=position)
message = 'Successfully added the image “{}” {} page {} of the PDF ' \
'file “{}”. Result: “{}”'
print(message.format(image, position, number, main_pdf, joined_pdf))
elif args.subcmd_args in ['convert', 'cv', 'c']:
if image.extension == 'pdf':
raise ('Specify an image file, not a PDF file.')
result_pdf = main_pdf.new(append='_insert')
os.rename(str(insert_pdf), str(result_pdf))
message = 'Successfully converted the image “{}” to the PDF file ' \
'“{}” using the dimensions of the PDF “{}”.'
print(message.format(image, result_pdf, main_pdf))
elif args.subcmd_args in ['replace', 're', 'r']:
joined_pdf = assemble_pdf(main_pdf,
insert_pdf,
info['page_count'],
args.number,
mode='replace')
message = 'Successfully replaced page {} of the PDF file “{}” with ' \
'the image “{}”. Result: “{}”'
print(message.format(number, main_pdf, image, joined_pdf))
def test_method_new(self):
path = FilePath('test.jpg')
self.assertEqual(str(path.new()), 'test.jpg')
self.assertEqual(str(path.new(extension='png')), 'test.png')
self.assertEqual(str(path.new(append='123')), 'test123.jpg')
self.assertEqual(str(path.new(del_substring='est')), 't.jpg')