paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-28 18:24:38 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'dev' into feature-permissions

Browse Source
This commit is contained in:
Michael Shamoon
2023-01-27 12:35:48 -08:00
parent 118e3703dc d2b290f789
commit d15773f282
21 changed files with 854 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/documents/views.py
View File

@@ -481,6 +481,10 @@ class DocumentViewSet(
)
c.save()
from documents import index
index.add_or_update_document(self.get_object())
return Response(self.getComments(doc))
except Exception as e:
logger.warning(f"An error occurred saving comment: {str(e)}")
@@ -492,6 +496,11 @@ class DocumentViewSet(
elif request.method == "DELETE":
comment = Comment.objects.get(id=int(request.GET.get("id")))
comment.delete()
from documents import index
index.add_or_update_document(self.get_object())
return Response(self.getComments(doc))
return Response(
@@ -504,21 +513,14 @@ class DocumentViewSet(
class SearchResultSerializer(DocumentSerializer, PassUserMixin):
def to_representation(self, instance):
doc = Document.objects.get(id=instance["id"])
comments = ""
if hasattr(instance.results.q, "subqueries"):
commentTerm = instance.results.q.subqueries[0]
comments = ",".join(
[
str(c.comment)
for c in Comment.objects.filter(document=instance["id"])
if commentTerm.text in c.comment
],
)
comments = ",".join(
[str(c.comment) for c in Comment.objects.filter(document=instance["id"])],
)
r = super().to_representation(doc)
r["__search_hit__"] = {
"score": instance.score,
"highlights": instance.highlights("content", text=doc.content),
"comment_highlights": instance.highlights("content", text=comments)
"comment_highlights": instance.highlights("comments", text=comments)
if doc
else None,
"rank": instance.rank,

2
src/paperless/version.py
View File

@@ -1,7 +1,7 @@
from typing import Final
from typing import Tuple
__version__: Final[Tuple[int, int, int]] = (1, 12, 0)
__version__: Final[Tuple[int, int, int]] = (1, 12, 1)
# Version string like X.Y.Z
__full_version_str__: Final[str] = ".".join(map(str, __version__))
# Version string like X.Y

10
src/paperless_mail/parsers.py
View File

@@ -271,6 +271,16 @@ class MailDocumentParser(DocumentParser):
"paperHeight": "11.7",
"scale": "1.0",
}
# Set the output format of the resulting PDF
# Valid inputs: https://gotenberg.dev/docs/modules/pdf-engines#uno
if settings.OCR_OUTPUT_TYPE in {"pdfa", "pdfa-2"}:
data["pdfFormat"] = "PDF/A-2b"
elif settings.OCR_OUTPUT_TYPE == "pdfa-1":
data["pdfFormat"] = "PDF/A-1a"
elif settings.OCR_OUTPUT_TYPE == "pdfa-3":
data["pdfFormat"] = "PDF/A-3b"
try:
response = requests.post(
url,

9
src/paperless_mail/tests/test_parsers.py
View File

@@ -573,8 +573,8 @@ class TestParser(TestCase):
self.parser.gotenberg_server + "/forms/chromium/convert/html",
mock_post.call_args.args[0],
)
self.assertEqual({}, mock_post.call_args.kwargs["headers"])
self.assertEqual(
self.assertDictEqual({}, mock_post.call_args.kwargs["headers"])
self.assertDictEqual(
{
"marginTop": "0.1",
"marginBottom": "0.1",
@@ -583,6 +583,7 @@ class TestParser(TestCase):
"paperWidth": "8.27",
"paperHeight": "11.7",
"scale": "1.0",
"pdfFormat": "PDF/A-2b",
},
mock_post.call_args.kwargs["data"],
)
@@ -663,8 +664,8 @@ class TestParser(TestCase):
self.parser.gotenberg_server + "/forms/chromium/convert/html",
mock_post.call_args.args[0],
)
self.assertEqual({}, mock_post.call_args.kwargs["headers"])
self.assertEqual(
self.assertDictEqual({}, mock_post.call_args.kwargs["headers"])
self.assertDictEqual(
{
"marginTop": "0.1",
"marginBottom": "0.1",

12
src/paperless_tika/parsers.py
View File

@@ -95,9 +95,19 @@ class TikaDocumentParser(DocumentParser):
),
}
headers = {}
data = {}
# Set the output format of the resulting PDF
# Valid inputs: https://gotenberg.dev/docs/modules/pdf-engines#uno
if settings.OCR_OUTPUT_TYPE in {"pdfa", "pdfa-2"}:
data["pdfFormat"] = "PDF/A-2b"
elif settings.OCR_OUTPUT_TYPE == "pdfa-1":
data["pdfFormat"] = "PDF/A-1a"
elif settings.OCR_OUTPUT_TYPE == "pdfa-3":
data["pdfFormat"] = "PDF/A-3b"
try:
response = requests.post(url, files=files, headers=headers)
response = requests.post(url, files=files, headers=headers, data=data)
response.raise_for_status() # ensure we notice bad responses
except Exception as err:
raise ParseError(