def test_right_to_left(self):
doc = Document("tests/resources/Fairy-Circles-Truly-a-Fairy-Tale-R-FKB-Kids-Stories_FA.pdf")
text = ""
for page in doc:
text += ' \n'.join(page.lines).strip()
with open("tests/resources/Fairy-Circles-Truly-a-Fairy-Tale-R-FKB-Kids-Stories_FA.txt", "r") as f:
correct = f.read()
assert correct == text
def ingest(self, file_path, entity):
"""Ingestor implementation."""
try:
pdf = Document(bytes(file_path))
except Exception as ex:
raise ProcessingException("Could not extract PDF file: %r" % ex) from ex # noqa
self.extract_metadata(pdf, entity)
self.extract_xmp_metadata(pdf, entity)
self.pdf_extract(entity, pdf)
def pdf_alternative_extract(self, entity, pdf_path):
checksum = self.manager.store(pdf_path)
entity.set('pdfHash', checksum)
pdf = Document(bytes(pdf_path))
self.pdf_extract(entity, pdf)
parser = argparse.ArgumentParser(
description="checks for presence of absence of text on images")
parser.add_argument("input_files", type=str, nargs="+", help="path to a PDF")
parser.add_argument(
"--threshold",
type=int,
default=0,
help="maximum number of chars to consider a page empty",
)
parser.add_argument("--absence",
action="store_true",
help="returnes pages without text")
args = parser.parse_args()
for input_file in args.input_files:
doc = Document(input_file)
output = []
num_pages = 0
for idx, page in enumerate(doc):
num_pages += 1
num_chars = sum(map(len, page.lines))
if num_chars > args.threshold:
output.append(idx + 1) # 1-based for PDFs
if args.absence:
output = list(set(range(1, num_pages + 1)).difference(set(output)))
print(" ".join(map(str, output)))
def test_empty_pdf(self):
with pytest.raises(IOError):
Document("tests/resources/empty.pdf")
def test_non_pdf_file(self):
with pytest.raises(IOError):
Document("tests/resources/not-pdf.txt")
def test_directory_path(self):
with pytest.raises(IOError):
Document("test/resources/")
def test_non_existent_file(self):
with pytest.raises(IOError):
Document("tests/resources/not-exists.pdf")
def test_extract_metadata(self):
doc = Document("tests/resources/FAC.pdf")
assert doc.metadata
assert doc.xmp_metadata
def test_extract_text(self):
doc = Document("tests/resources/prop.pdf")
text = ""
for page in doc:
text += ' \n'.join(page.lines).strip()
assert "Milestones" in text
def test_bytes_paths(self):
self._clean_images()
doc = Document(b"tests/resources/FAC.pdf")
doc.extract_images(path=b"tests/images", prefix="img")
assert os.path.exists("tests/images")
assert len(glob.glob(os.path.join("tests/images", "*.png"))) == 4
def test_extract_images(self, path, no_imgs):
self._clean_images()
doc = Document(path)
doc.extract_images(path="tests/images", prefix="img")
assert os.path.exists("tests/images")
assert len(glob.glob(os.path.join("tests/images", "*.png"))) == no_imgs
def pdf_alternative_extract(self, pdf_path):
self.result.emit_pdf_alternative(pdf_path)
pdf = Document(pdf_path.encode('utf-8'))
self.pdf_extract(pdf)
def pdf_alternative_extract(self, pdf_path):
pdf = Document(pdf_path.encode('utf-8'))
self.pdf_extract(pdf)