lgcosta/paperless-ngx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Split

Browse Source
This commit is contained in:
shamoon
2024-03-03 12:23:43 -08:00
parent d5eedbab0d
commit 713598d86b
12 changed files with 468 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
src/documents/bulk_edit.py
View File

@@ -212,31 +212,13 @@ def merge(doc_ids: list[int], metadata_document_id: Optional[int] = None):
)
merged_pdf.save(filepath)
overrides = DocumentMetadataOverrides()
if metadata_document_id:
metadata_document = qs.get(id=metadata_document_id)
if metadata_document is not None:
overrides = DocumentMetadataOverrides.from_document(metadata_document)
overrides.title = metadata_document.title + " (merged)"
overrides.correspondent_id = (
metadata_document.correspondent.pk
if metadata_document.correspondent
else None
)
overrides.document_type_id = (
metadata_document.document_type.pk
if metadata_document.document_type
else None
)
overrides.storage_path_id = (
metadata_document.storage_path.pk
if metadata_document.storage_path
else None
)
overrides.tag_ids = list(
metadata_document.tags.values_list("id", flat=True),
)
# Include owner and permissions?
else:
overrides = DocumentMetadataOverrides()
logger.info("Adding merged document to the task queue.")
consume_file.delay(
@@ -248,3 +230,42 @@ def merge(doc_ids: list[int], metadata_document_id: Optional[int] = None):
)
return "OK"
def split(doc_ids: list[int], pages: list[list[int]]):
logger.info(
f"Attempting to split document {doc_ids[0]} into {len(pages)} documents",
)
doc = Document.objects.get(id=doc_ids[0])
import pikepdf
path = os.path.join(settings.ORIGINALS_DIR, str(doc.filename))
try:
with pikepdf.open(path, allow_overwriting_input=True) as pdf:
for idx, split_doc in enumerate(pages):
dst = pikepdf.new()
for page in split_doc:
dst.pages.append(pdf.pages[page - 1])
filepath = os.path.join(
settings.CONSUMPTION_DIR,
f"{doc.filename}_{split_doc[0]}-{split_doc[-1]}.pdf",
)
dst.save(filepath)
overrides = DocumentMetadataOverrides().from_document(doc)
overrides.title = f"{doc.title} (split {idx + 1})"
logger.info(
f"Adding split document with pages {split_doc} to the task queue.",
)
consume_file.delay(
ConsumableDocument(
source=DocumentSource.ConsumeFolder,
original_file=filepath,
),
overrides,
)
except Exception as e:
logger.exception(f"Error splitting document {doc.id}", e)
return "OK"

36
src/documents/data_models.py
View File

@@ -5,6 +5,8 @@ from pathlib import Path
from typing import Optional
import magic
from guardian.shortcuts import get_groups_with_perms
from guardian.shortcuts import get_users_with_perms
@dataclasses.dataclass
@@ -88,6 +90,40 @@ class DocumentMetadataOverrides:
return self
@staticmethod
def from_document(doc) -> "DocumentMetadataOverrides":
"""
Fills in the overrides from a document object
"""
overrides = DocumentMetadataOverrides()
overrides.title = doc.title
overrides.correspondent_id = doc.correspondent.id if doc.correspondent else None
overrides.document_type_id = doc.document_type.id if doc.document_type else None
overrides.storage_path_id = doc.storage_path.id if doc.storage_path else None
overrides.owner_id = doc.owner.id if doc.owner else None
overrides.tag_ids = list(doc.tags.values_list("id", flat=True))
overrides.view_users = get_users_with_perms(
doc,
only_with_perms_in=["view_document"],
).values_list("id", flat=True)
overrides.view_groups = get_groups_with_perms(
doc,
only_with_perms_in=["view_document"],
).values_list("id", flat=True)
overrides.change_users = get_users_with_perms(
doc,
only_with_perms_in=["change_document"],
).values_list("id", flat=True)
overrides.change_groups = get_groups_with_perms(
doc,
only_with_perms_in=["change_document"],
).values_list("id", flat=True)
overrides.custom_field_ids = list(
doc.custom_fields.values_list("id", flat=True),
)
return overrides
class DocumentSource(IntEnum):
"""

32
src/documents/serialisers.py
View File

@@ -871,6 +871,7 @@ class BulkEditSerializer(DocumentListSerializer, SetPermissionsMixin):
"set_permissions",
"rotate",
"merge",
"split",
],
label="Method",
write_only=True,
@@ -912,6 +913,8 @@ class BulkEditSerializer(DocumentListSerializer, SetPermissionsMixin):
return bulk_edit.rotate
elif method == "merge":
return bulk_edit.merge
elif method == "split":
return bulk_edit.split
else:
raise serializers.ValidationError("Unsupported method.")
@@ -1000,6 +1003,29 @@ class BulkEditSerializer(DocumentListSerializer, SetPermissionsMixin):
except ValueError:
raise serializers.ValidationError("invalid rotation degrees")
def _validate_parameters_split(self, parameters):
if "pages" not in parameters:
raise serializers.ValidationError("pages not specified")
try:
pages = []
docs = parameters["pages"].split(",")
for doc in docs:
if "-" in doc:
pages.append(
[
x
for x in range(
int(doc.split("-")[0]),
int(doc.split("-")[1]) + 1,
)
],
)
else:
pages.append([int(doc)])
parameters["pages"] = pages
except ValueError:
raise serializers.ValidationError("invalid pages specified")
def validate(self, attrs):
method = attrs["method"]
parameters = attrs["parameters"]
@@ -1018,6 +1044,12 @@ class BulkEditSerializer(DocumentListSerializer, SetPermissionsMixin):
self._validate_parameters_set_permissions(parameters)
elif method == bulk_edit.rotate:
self._validate_parameters_rotate(parameters)
elif method == bulk_edit.split:
if len(attrs["documents"]) > 1:
raise serializers.ValidationError(
"Split method only supports one document",
)
self._validate_parameters_split(parameters)
return attrs

72
src/documents/tests/test_api_bulk_edit.py
View File

@@ -859,3 +859,75 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
args, kwargs = m.call_args
self.assertCountEqual(args[0], [self.doc2.id, self.doc3.id])
self.assertEqual(kwargs["metadata_document_id"], self.doc3.id)
@mock.patch("documents.serialisers.bulk_edit.split")
def test_split(self, m):
m.return_value = "OK"
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc2.id],
"method": "split",
"parameters": {"pages": "1,2-4,5-6,7"},
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_200_OK)
m.assert_called_once()
args, kwargs = m.call_args
self.assertCountEqual(args[0], [self.doc2.id])
self.assertEqual(kwargs["pages"], [[1], [2, 3, 4], [5, 6], [7]])
def test_split_invalid_params(self):
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc2.id],
"method": "split",
"parameters": {}, # pages not specified
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn(b"pages not specified", response.content)
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [self.doc2.id],
"method": "split",
"parameters": {"pages": "1:7"}, # wrong format
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn(b"invalid pages specified", response.content)
response = self.client.post(
"/api/documents/bulk_edit/",
json.dumps(
{
"documents": [
self.doc1.id,
self.doc2.id,
], # only one document supported
"method": "split",
"parameters": {"pages": "1-2,3-7"}, # wrong format
},
),
content_type="application/json",
)
self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
self.assertIn(b"Split method only supports one document", response.content)