def test_preview(self):
doc = Document.create_document(
title="andromeda.pdf",
user=self.testcase_user,
lang="ENG",
file_name="andromeda.pdf",
size=1222,
page_count=3
)
copy2doc_url(
src_file_path=os.path.join(
BASE_DIR, "data", "andromeda.pdf"
),
doc_url=doc.doc_ep.url()
)
ret = self.client.post(
reverse('core:preview', args=(doc.id, 1, 1))
)
self.assertEqual(
ret.status_code,
200
)
page_url = PageEp(
document_ep=doc.doc_ep,
page_num=1,
step=Step(1),
page_count=3
)
self.assertTrue(
os.path.exists(page_url.img_exists())
)
def preview(request, id, step=None, page="1"):
try:
doc = Document.objects.get(id=id)
except Document.DoesNotExist:
raise Http404("Document does not exists")
if request.user.has_perm(Access.PERM_READ, doc):
doc_ep = doc.doc_ep
if not doc_ep.exists():
download(doc_ep)
page_ep = doc.get_page_ep(
page_num=page,
step=Step(step),
)
if not page_ep.img_exists():
extract_img(page_ep)
try:
with open(page_ep.img_url(), "rb") as f:
return HttpResponse(f.read(), content_type="image/jpeg")
except IOError:
raise
return redirect('core:index')
def test_hocr_exists(self):
local_media = os.path.join(os.path.dirname(os.path.dirname(__file__)),
"test", "media")
remote_ep = Endpoint("s3:/test-papermerge/")
local_ep = Endpoint(f"local:{local_media}")
doc_ep = DocumentEp(remote_endpoint=remote_ep,
local_endpoint=local_ep,
user_id=1,
document_id=3,
file_name="x.pdf")
page_ep1 = PageEp(document_ep=doc_ep,
page_num=1,
step=Step(1),
page_count=3)
self.assertTrue(page_ep1.hocr_exists())
page_ep2 = PageEp(document_ep=doc_ep,
page_num=2,
step=Step(1),
page_count=3)
self.assertFalse(page_ep2.hocr_exists())
def test_ppmroot(self):
doc_ep = DocumentEp(remote_endpoint=self.remote_ep,
local_endpoint=self.local_ep,
user_id=1,
document_id=3,
file_name="x.pdf")
page_url = PageEp(document_ep=doc_ep,
page_num=1,
step=Step(1),
page_count=3)
self.assertEqual(page_url.ppmroot,
(f"/var/media/results/user_1/"
f"document_3/pages/page_1/100/page"))
def test_txt_url(self):
"""
Without any arguments
page_ep.url() returns page_ep.txt_url()
"""
doc_ep = DocumentEp(remote_endpoint=self.remote_ep,
local_endpoint=self.local_ep,
user_id=1,
document_id=3,
file_name="x.pdf")
page_ep = PageEp(document_ep=doc_ep,
page_num=1,
step=Step(1),
page_count=3)
self.assertEqual(page_ep.url(), page_ep.txt_url())
def ocr_page_pdf(doc_ep, page_num, lang):
page_count = get_pagecount(doc_ep.url())
logger.debug(f"page_count={page_count}")
if page_num <= page_count:
page_url = PageEp(document_ep=doc_ep,
page_num=page_num,
step=Step(1),
page_count=page_count)
extract_img(page_url)
extract_txt(page_url, lang=lang)
for step in Steps():
page_url.step = step
extract_img(page_url)
# tesseract unterhalt-1.jpg page-1 -l deu hocr
if not step.is_thumbnail:
extract_hocr(page_url, lang=lang)
return page_url
def test_step(self):
step = Step(1)
self.assertFalse(step.is_thumbnail,
f"{step} is is_thumbnail, but it should not be!")