Split

src-ui/src/app/app.module.ts

@@ -118,6 +118,7 @@ import { SystemStatusDialogComponent } from './components/common/system-status-d
 import { NgxFilesizeModule } from 'ngx-filesize'
 import { RotateConfirmDialogComponent } from './components/common/confirm-dialog/rotate-confirm-dialog/rotate-confirm-dialog.component'
 import { MergeConfirmDialogComponent } from './components/common/confirm-dialog/merge-confirm-dialog/merge-confirm-dialog.component'
+import { SplitConfirmDialogComponent } from './components/common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component'
 import {
   airplane,
   archive,
@@ -193,6 +194,7 @@ import {
   plus,
   plusCircle,
   questionCircle,
+  scissors,
   search,
   slashCircle,
   sliders2Vertical,
@@ -286,6 +288,7 @@ const icons = {
   plus,
   plusCircle,
   questionCircle,
+  scissors,
   search,
   slashCircle,
   sliders2Vertical,
@@ -468,6 +471,7 @@ function initializeApp(settings: SettingsService) {
     SystemStatusDialogComponent,
     RotateConfirmDialogComponent,
     MergeConfirmDialogComponent,
+    SplitConfirmDialogComponent,
   ],
   imports: [
     BrowserModule,

src-ui/src/app/components/common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component.html

@@ -0,0 +1,55 @@
+<div class="modal-header">
+    <h4 class="modal-title" id="modal-basic-title">{{title}}</h4>
+    <button type="button" class="btn-close" aria-label="Close" (click)="cancel()">
+    </button>
+  </div>
+  <div class="modal-body">
+    <p>{{message}}</p>
+    <div class="row mb-2">
+        <div class="col-6">
+            <div class="input-group input-group-sm">
+              <div class="input-group-text" i18n>Page</div>
+              <input class="form-control" type="number" min="1" [(ngModel)]="page" />
+              <div class="input-group-text" i18n>of {{totalPages}}</div>
+            </div>
+            <div class="pdf-viewer-container w-100 mt-3">
+                <pngx-pdf-viewer [src]="pdfSrc" [(page)]="page"
+                [original-size]="false"
+                [zoom]="1"
+                zoom-scale="page-fit"
+                (after-load-complete)="pdfPreviewLoaded($event)">
+                </pngx-pdf-viewer>
+            </div>
+        </div>
+        <div class="col-6">
+            <div class="d-grid">
+                <button class="btn btn-sm btn-primary" (click)="addSplit()">
+                    <i-bs name="plus-circle"></i-bs>&nbsp;
+                    <span i18n>Add Split</span>
+                </button>
+            </div>
+
+            <ul class="list-group mt-3">
+                @for (pageStr of pagesString.split(','); track pageStr; let i = $index) {
+                    <li class="list-group-item">
+                        {{pageStr}}
+                        @if (pagesString.split(',').length > 1) {
+                            &nbsp;
+                            <button class="btn btn-sm btn-danger" (click)="removeSplit(i)">
+                                <i-bs name="trash"></i-bs>
+                            </button>
+                        }
+                    </li>
+                }
+            </ul>
+        </div>
+    </div>
+  </div>
+  <div class="modal-footer">
+    <button type="button" class="btn" [class]="cancelBtnClass" (click)="cancel()" [disabled]="!buttonsEnabled">
+          <span class="d-inline-block" style="padding-bottom: 1px;">{{cancelBtnCaption}}</span>
+        </button>
+    <button type="button" class="btn" [class]="btnClass" (click)="confirm()" [disabled]="!confirmButtonEnabled || !buttonsEnabled">
+        {{btnCaption}}
+    </button>
+  </div>

src-ui/src/app/components/common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component.scss

@@ -0,0 +1,9 @@
+.pdf-viewer-container {
+    background-color: gray;
+    height: 300px;
+
+    pngx-pdf-viewer {
+      width: 100%;
+      height: 100%;
+    }
+  }

src-ui/src/app/components/common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component.spec.ts

@@ -0,0 +1,81 @@
+import { ComponentFixture, TestBed } from '@angular/core/testing'
+
+import { SplitConfirmDialogComponent } from './split-confirm-dialog.component'
+import { HttpClientTestingModule } from '@angular/common/http/testing'
+import { ReactiveFormsModule, FormsModule } from '@angular/forms'
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
+import { NgxBootstrapIconsModule, allIcons } from 'ngx-bootstrap-icons'
+import { DocumentService } from 'src/app/services/rest/document.service'
+import { PdfViewerComponent } from '../../pdf-viewer/pdf-viewer.component'
+
+describe('SplitConfirmDialogComponent', () => {
+  let component: SplitConfirmDialogComponent
+  let fixture: ComponentFixture<SplitConfirmDialogComponent>
+  let documentService: DocumentService
+
+  beforeEach(async () => {
+    await TestBed.configureTestingModule({
+      declarations: [SplitConfirmDialogComponent, PdfViewerComponent],
+      providers: [NgbActiveModal],
+      imports: [
+        HttpClientTestingModule,
+        NgxBootstrapIconsModule.pick(allIcons),
+        ReactiveFormsModule,
+        FormsModule,
+      ],
+    }).compileComponents()
+
+    fixture = TestBed.createComponent(SplitConfirmDialogComponent)
+    documentService = TestBed.inject(DocumentService)
+    component = fixture.componentInstance
+    fixture.detectChanges()
+  })
+
+  it('should update pagesString when pages are added', () => {
+    component.totalPages = 5
+    component.page = 2
+    component.addSplit()
+    expect(component.pagesString).toEqual('1-2,3-5')
+    component.page = 4
+    component.addSplit()
+    expect(component.pagesString).toEqual('1-2,3-4,5')
+  })
+
+  it('should update pagesString when pages are removed', () => {
+    component.totalPages = 5
+    component.page = 2
+    component.addSplit()
+    component.page = 4
+    component.addSplit()
+    expect(component.pagesString).toEqual('1-2,3-4,5')
+    component.removeSplit(0)
+    expect(component.pagesString).toEqual('1-4,5')
+  })
+
+  it('should enable confirm button when pages are added', () => {
+    component.totalPages = 5
+    component.page = 2
+    component.addSplit()
+    expect(component.confirmButtonEnabled).toBeTruthy()
+  })
+
+  it('should disable confirm button when all pages are removed', () => {
+    component.totalPages = 5
+    component.page = 2
+    component.addSplit()
+    component.removeSplit(0)
+    expect(component.confirmButtonEnabled).toBeFalsy()
+  })
+
+  it('should not add split if page is the last page', () => {
+    component.totalPages = 5
+    component.page = 5
+    component.addSplit()
+    expect(component.pagesString).toEqual('1-5')
+  })
+
+  it('should update totalPages when pdf is loaded', () => {
+    component.pdfPreviewLoaded({ numPages: 5 } as any)
+    expect(component.totalPages).toEqual(5)
+  })
+})

src-ui/src/app/components/common/confirm-dialog/split-confirm-dialog/split-confirm-dialog.component.ts

@@ -0,0 +1,66 @@
+import { Component } from '@angular/core'
+import { ConfirmDialogComponent } from '../confirm-dialog.component'
+import { NgbActiveModal } from '@ng-bootstrap/ng-bootstrap'
+import { DocumentService } from 'src/app/services/rest/document.service'
+import { PDFDocumentProxy } from '../../pdf-viewer/typings'
+
+@Component({
+  selector: 'pngx-split-confirm-dialog',
+  templateUrl: './split-confirm-dialog.component.html',
+  styleUrl: './split-confirm-dialog.component.scss',
+})
+export class SplitConfirmDialogComponent extends ConfirmDialogComponent {
+  public get pagesString(): string {
+    let pagesStr = ''
+
+    let lastPage = 1
+    for (let i = 1; i <= this.totalPages; i++) {
+      if (this.pages.has(i) || i === this.totalPages) {
+        if (lastPage === i) {
+          pagesStr += `${i},`
+          lastPage = Math.min(i + 1, this.totalPages)
+        } else {
+          pagesStr += `${lastPage}-${i},`
+          lastPage = Math.min(i + 1, this.totalPages)
+        }
+      }
+    }
+
+    return pagesStr.replace(/,$/, '')
+  }
+
+  private pages: Set<number> = 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
+  }
+}

src-ui/src/app/components/document-detail/document-detail.component.html

@@ -44,11 +44,15 @@
     </button>
     <div ngbDropdownMenu aria-labelledby="actionsDropdown" class="shadow">
       <button ngbDropdownItem (click)="redoOcr()" [disabled]="!userCanEdit">
-        <i-bs width="1em" height="1em" name="arrow-counterclockwise"></i-bs><span class="ps-1" i18n>Redo OCR</span>
+        <i-bs width="1em" height="1em" name="arrow-counterclockwise"></i-bs>&nbsp;<span i18n>Redo OCR</span>
       </button>
 
       <button ngbDropdownItem (click)="moreLike()">
-        <i-bs width="1em" height="1em" name="diagram-3"></i-bs><span class="ps-1" i18n>More like this</span>
+        <i-bs width="1em" height="1em" name="diagram-3"></i-bs>&nbsp;<span i18n>More like this</span>
+      </button>
+
+      <button ngbDropdownItem (click)="splitDocument()" [disabled]="contentRenderType !== ContentRenderType.PDF">
+        <i-bs width="1em" height="1em" name="scissors"></i-bs>&nbsp;<span i18n>Split</span>
       </button>
     </div>
   </div>

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')

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
+              )
+            },
+          })
+      })
+  }
 }

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 = (
+    else:
-                metadata_document.correspondent.pk
+        overrides = DocumentMetadataOverrides()
-                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?
 
     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"

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):
     """

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
 

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)