def test_jbig2_image_export(self):
"""Extract images of pdf containing jbig2 images
Feature test for: https://github.com/pdfminer/pdfminer.six/pull/46
"""
image_files = self.extract_images(
absolute_sample_path('../samples/contrib/pdf-with-jbig2.pdf'))
assert image_files[0].endswith('.jb2')
def run(filename, options=None):
absolute_path = absolute_sample_path(filename)
with NamedTemporaryFile() as output_file:
if options:
s = 'dumppdf -o %s %s %s' % (output_file.name, options,
absolute_path)
else:
s = 'dumppdf -o %s %s' % (output_file.name, absolute_path)
dumppdf.main(s.split(' ')[1:])
def test_nonfree_dmca(self):
"""Extract images of pdf containing bmp images
Regression test for:
https://github.com/pdfminer/pdfminer.six/issues/131
"""
image_files = self.extract_images(
absolute_sample_path('../samples/nonfree/dmca.pdf'))
assert image_files[0].endswith('bmp')
def run(sample_path, options=None):
absolute_path = absolute_sample_path(sample_path)
with NamedTemporaryFile() as output_file:
if options:
s = 'pdf2txt -o{} {} {}' \
.format(output_file.name, options, absolute_path)
else:
s = 'pdf2txt -o{} {}'.format(output_file.name, absolute_path)
pdf2txt.main(s.split(' ')[1:])
def test_font_size():
path = absolute_sample_path('font-size-test.pdf')
for page in extract_pages(path):
for text_box in page:
if isinstance(text_box, LTTextBox):
for line in text_box:
possible_number = line.get_text().strip()
if possible_number.isdigit():
expected_size = int(possible_number)
for char in line:
if isinstance(char, LTChar):
actual_size = int(round(char.size))
print(char, actual_size, expected_size)
assert expected_size == actual_size
else:
print(repr(line.get_text()))
def _get_test_file_path(self):
test_file = "simple4.pdf"
return absolute_sample_path(test_file)
def run_with_string(sample_path, laparams=None):
if laparams is None:
laparams = {}
absolute_path = absolute_sample_path(sample_path)
s = extract_text(absolute_path, laparams=LAParams(**laparams))
return s
def run_with_file(sample_path):
absolute_path = absolute_sample_path(sample_path)
with open(absolute_path, "rb") as in_file:
s = extract_text(in_file)
return s
def run(sample_path):
absolute_path = absolute_sample_path(sample_path)
s = extract_text(absolute_path)
return s
def test_nonfree_175(self):
"""Extract images of pdf containing jpg images"""
self.extract_images(absolute_sample_path('../samples/nonfree/175.pdf'))
def test_string_input(self):
filename = absolute_sample_path("simple1.pdf")
opened = open_filename(filename)
assert_equal(opened.closing, True)
def test_file_input(self):
filename = absolute_sample_path("simple1.pdf")
with open(filename, "rb") as in_file:
opened = open_filename(in_file)
assert_equal(opened.file_handler, in_file)
def test_pathlib_input(self):
filename = pathlib.Path(absolute_sample_path("simple1.pdf"))
opened = open_filename(filename)
assert_equal(opened.closing, True)
