= new Set()
+
+ public documentID: number
+ public page: number = 1
+ public totalPages: number
+
+ public get pdfSrc(): string {
+ return this.documentService.getPreviewUrl(this.documentID)
+ }
+
+ constructor(
+ activeModal: NgbActiveModal,
+ private documentService: DocumentService
+ ) {
+ super(activeModal)
+ this.confirmButtonEnabled = this.pages.size > 0
+ }
+
+ pdfPreviewLoaded(pdf: PDFDocumentProxy) {
+ this.totalPages = pdf.numPages
+ }
+
+ addSplit() {
+ if (this.page === this.totalPages) return
+ this.pages.add(this.page)
+ this.pages = new Set(Array.from(this.pages).sort())
+ this.confirmButtonEnabled = this.pages.size > 0
+ }
+
+ removeSplit(i: number) {
+ let page = Array.from(this.pages)[Math.min(i, this.pages.size - 1)]
+ this.pages.delete(page)
+ this.confirmButtonEnabled = this.pages.size > 0
+ }
+}
diff --git a/src-ui/src/app/components/document-detail/document-detail.component.html b/src-ui/src/app/components/document-detail/document-detail.component.html
index 5b27a51ac..4e8443b02 100644
--- a/src-ui/src/app/components/document-detail/document-detail.component.html
+++ b/src-ui/src/app/components/document-detail/document-detail.component.html
@@ -44,11 +44,15 @@
+
+
diff --git a/src-ui/src/app/components/document-detail/document-detail.component.spec.ts b/src-ui/src/app/components/document-detail/document-detail.component.spec.ts
index e0da11a3e..7663657c0 100644
--- a/src-ui/src/app/components/document-detail/document-detail.component.spec.ts
+++ b/src-ui/src/app/components/document-detail/document-detail.component.spec.ts
@@ -1070,6 +1070,33 @@ describe('DocumentDetailComponent', () => {
).not.toBeUndefined()
})
+ it('should support split', () => {
+ let modal: NgbModalRef
+ modalService.activeInstances.subscribe((m) => (modal = m[0]))
+ initNormally()
+ component.splitDocument()
+ expect(modal).not.toBeUndefined()
+ modal.componentInstance.documentID = doc.id
+ modal.componentInstance.totalPages = 5
+ modal.componentInstance.page = 2
+ modal.componentInstance.addSplit()
+ modal.componentInstance.confirm()
+ let req = httpTestingController.expectOne(
+ `${environment.apiBaseUrl}documents/bulk_edit/`
+ )
+ expect(req.request.body).toEqual({
+ documents: [doc.id],
+ method: 'split',
+ parameters: { pages: '1-2,3-5' },
+ })
+ req.error(new ProgressEvent('failed'))
+ modal.componentInstance.confirm()
+ req = httpTestingController.expectOne(
+ `${environment.apiBaseUrl}documents/bulk_edit/`
+ )
+ req.flush(true)
+ })
+
function initNormally() {
jest
.spyOn(activatedRoute, 'paramMap', 'get')
diff --git a/src-ui/src/app/components/document-detail/document-detail.component.ts b/src-ui/src/app/components/document-detail/document-detail.component.ts
index 4eae47615..0c61044aa 100644
--- a/src-ui/src/app/components/document-detail/document-detail.component.ts
+++ b/src-ui/src/app/components/document-detail/document-detail.component.ts
@@ -67,6 +67,7 @@ import { CustomField, CustomFieldDataType } from 'src/app/data/custom-field'
import { CustomFieldInstance } from 'src/app/data/custom-field-instance'
import { CustomFieldsService } from 'src/app/services/rest/custom-fields.service'
import { PDFDocumentProxy } from '../common/pdf-viewer/typings'
+import { SplitConfirmDialogComponent } from '../common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component'
enum DocumentDetailNavIDs {
Details = 1,
@@ -1040,4 +1041,41 @@ export class DocumentDetailComponent
this.updateFormForCustomFields(true)
this.documentForm.updateValueAndValidity()
}
+
+ splitDocument() {
+ let modal = this.modalService.open(SplitConfirmDialogComponent, {
+ backdrop: 'static',
+ })
+ modal.componentInstance.title = $localize`Split confirm`
+ modal.componentInstance.messageBold = $localize`This operation will split the selected document(s) into new documents.`
+ modal.componentInstance.btnCaption = $localize`Proceed`
+ modal.componentInstance.documentID = this.document.id
+ modal.componentInstance.confirmClicked
+ .pipe(takeUntil(this.unsubscribeNotifier))
+ .subscribe(() => {
+ modal.componentInstance.buttonsEnabled = false
+ this.documentsService
+ .bulkEdit([this.document.id], 'split', {
+ pages: modal.componentInstance.pagesString,
+ })
+ .pipe(first(), takeUntil(this.unsubscribeNotifier))
+ .subscribe({
+ next: () => {
+ this.toastService.showInfo(
+ $localize`Split operation will begin in the background.`
+ )
+ modal.close()
+ },
+ error: (error) => {
+ if (modal) {
+ modal.componentInstance.buttonsEnabled = true
+ }
+ this.toastService.showError(
+ $localize`Error executing split operation`,
+ error
+ )
+ },
+ })
+ })
+ }
}
diff --git a/src/documents/bulk_edit.py b/src/documents/bulk_edit.py
index 8f4cb05d1..1c1d3cf79 100644
--- a/src/documents/bulk_edit.py
+++ b/src/documents/bulk_edit.py
@@ -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"
diff --git a/src/documents/data_models.py b/src/documents/data_models.py
index 6bf3f4f96..34a2e8203 100644
--- a/src/documents/data_models.py
+++ b/src/documents/data_models.py
@@ -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):
"""
diff --git a/src/documents/serialisers.py b/src/documents/serialisers.py
index 5e9b3edbb..bdac7660e 100644
--- a/src/documents/serialisers.py
+++ b/src/documents/serialisers.py
@@ -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
diff --git a/src/documents/tests/test_api_bulk_edit.py b/src/documents/tests/test_api_bulk_edit.py
index e1af6830e..d659c82e8 100644
--- a/src/documents/tests/test_api_bulk_edit.py
+++ b/src/documents/tests/test_api_bulk_edit.py
@@ -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)