This is redundant now

.mypy-baseline.txt

@@ -38,7 +38,6 @@ src/documents/bulk_edit.py:0: error: Incompatible types in assignment (expressio
 src/documents/bulk_edit.py:0: error: Invalid index type "str" for "dict[FieldDataType, str]"; expected type "FieldDataType"  [index]
 src/documents/bulk_edit.py:0: error: List comprehension has incompatible type List[tuple[int, Any]]; expected List[int]  [misc]
 src/documents/bulk_edit.py:0: error: List comprehension has incompatible type List[tuple[int, None]]; expected List[int]  [misc]
-src/documents/bulk_edit.py:0: error: Missing named argument "p" for "remove" of "PageList"  [call-arg]
 src/documents/bulk_edit.py:0: error: Missing type arguments for generic type "dict"  [type-arg]
 src/documents/bulk_edit.py:0: error: Missing type arguments for generic type "dict"  [type-arg]
 src/documents/bulk_edit.py:0: error: Need type annotation for "to_create" (hint: "to_create: list[<type>] = ...")  [var-annotated]

.pyrefly-baseline.json

@@ -91,13 +91,6 @@
       "concise_description": "Argument `list[int]` is not assignable to parameter `args` with type `tuple[Any, ...] | None` in function `celery.app.task.Task.apply_async`",
       "severity": "error"
     },
-    {
-      "column": 33,
-      "path": "src/documents/bulk_edit.py",
-      "name": "missing-argument",
-      "concise_description": "Missing argument `p` in function `pikepdf._core.PageList.remove`",
-      "severity": "error"
-    },
     {
       "column": 25,
       "path": "src/documents/caching.py",

src/documents/bulk_edit.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import logging
 import tempfile
 import uuid
+from functools import partial
 from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Literal
@@ -13,16 +14,11 @@ from celery import group
 from celery import shared_task
 from django.conf import settings
 from django.db import transaction
-from django.db.models import Case
-from django.db.models import F
 from django.db.models import Max
-from django.db.models import OuterRef
 from django.db.models import Q
-from django.db.models import Subquery
-from django.db.models import When
-from django.db.models.functions import Coalesce
 from django.utils import timezone
 
+from documents import pdf_ops
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
@@ -42,7 +38,6 @@ from documents.tasks import remove_document_from_index
 from documents.tasks import update_document_content_maybe_archive_file
 from documents.versioning import get_latest_version_for_root
 from documents.versioning import get_root_document
-from documents.versioning import versions_newest_first
 
 if TYPE_CHECKING:
     from collections.abc import Mapping
@@ -123,6 +118,11 @@ def _resolve_root_and_source_doc(
     )
 
 
+def _scratch_path(name: str) -> Path:
+    """A path inside a fresh directory under SCRATCH_DIR."""
+    return Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR)) / name
+
+
 def set_correspondent(
     doc_ids: list[int],
     correspondent: Correspondent,
@@ -415,28 +415,10 @@ def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
 
     Consumption workflows do not run here, so ``remote_ocr`` is how the user
     asks for the remote engine when it is not configured to handle everything.
-
-    A root document with versions reprocesses its latest version, which is the
-    file whose content, archive and thumbnail are shown for it.
     """
-    latest_version = versions_newest_first(
-        Document.objects.filter(root_document=OuterRef("pk")),
-    ).values("id")[:1]
-    source_ids = (
-        Document.objects.filter(id__in=doc_ids)
-        .annotate(
-            source_id=Case(
-                When(root_document__isnull=False, then=F("id")),
-                default=Coalesce(Subquery(latest_version), F("id")),
-            ),
-        )
-        .order_by()
-        .values_list("source_id", flat=True)
-        .distinct()
-    )
-    for source_id in source_ids:
+    for document_id in doc_ids:
         update_document_content_maybe_archive_file.apply_async(
-            kwargs={"document_id": source_id, "remote_ocr": remote_ocr},
+            kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
             headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
         )
 
@@ -499,8 +481,6 @@ def rotate(
         pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
         docs_by_root_id.setdefault(pair.root_doc.id, pair)
 
-    import pikepdf
-
     for pair in docs_by_root_id.values():
         if pair.source_doc.mime_type != "application/pdf":
             logger.warning(
@@ -513,11 +493,7 @@ def rotate(
                 Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
                 / f"{pair.root_doc.id}_rotated.pdf"
             )
-            with pikepdf.open(pair.source_doc.source_path) as pdf:
-                for page in pdf.pages:
-                    page.rotate(degrees, relative=True)
-                pdf.remove_unreferenced_resources()
-                pdf.save(filepath)
+            pdf_ops.rotate_pdf(pair.source_doc.source_path, filepath, degrees)
 
             # Preserve metadata/permissions via overrides; mark as new version
             overrides = DocumentMetadataOverrides().from_document(pair.root_doc)
@@ -560,48 +536,45 @@ def merge(
     qs = Document.objects.select_related("root_document").filter(id__in=doc_ids)
     docs_by_id = {doc.id: doc for doc in qs}
     affected_docs: list[int] = []
-    import pikepdf
-
-    merged_pdf = pikepdf.new()
-    version: str = merged_pdf.pdf_version
     handoff_asn: int | None = None
-    # use doc_ids to preserve order
-    for doc_id in doc_ids:
-        doc = docs_by_id.get(doc_id)
-        if doc is None:
-            continue
-        pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
-        try:
-            doc_path = (
-                pair.source_doc.archive_path
-                if archive_fallback
-                and pair.source_doc.mime_type != "application/pdf"
-                and pair.source_doc.has_archive_version
-                else pair.source_doc.source_path
-            )
-            with pikepdf.open(str(doc_path)) as pdf:
-                version = max(version, pdf.pdf_version)
-                merged_pdf.pages.extend(pdf.pages)
-            affected_docs.append(doc.id)
-            if handoff_asn is None and doc.archive_serial_number is not None:
-                handoff_asn = doc.archive_serial_number
-        except Exception as e:
-            logger.exception(
-                f"Error merging document {doc.id}, it will not be included in the merge: {e}",
-            )
-    if len(affected_docs) == 0:
-        logger.warning("No documents were merged")
-        return "OK"
+    with pdf_ops.PdfMerger() as merger:
+        # use doc_ids to preserve order
+        for doc_id in doc_ids:
+            doc = docs_by_id.get(doc_id)
+            if doc is None:
+                continue
+            pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
+            try:
+                # archive_path is None when there is no archive version
+                archive_path = (
+                    pair.source_doc.archive_path
+                    if archive_fallback
+                    and pair.source_doc.mime_type != "application/pdf"
+                    else None
+                )
+                merger.add(
+                    archive_path
+                    if archive_path is not None
+                    else pair.source_doc.source_path,
+                )
+                affected_docs.append(doc.id)
+                if handoff_asn is None and doc.archive_serial_number is not None:
+                    handoff_asn = doc.archive_serial_number
+            except Exception as e:
+                logger.exception(
+                    f"Error merging document {doc.id}, it will not be included in the merge: {e}",
+                )
+        if len(affected_docs) == 0:
+            logger.warning("No documents were merged")
+            return "OK"
 
-    filepath = (
-        Path(
-            tempfile.mkdtemp(dir=settings.SCRATCH_DIR),
+        filepath = (
+            Path(
+                tempfile.mkdtemp(dir=settings.SCRATCH_DIR),
+            )
+            / f"{'_'.join([str(doc_id) for doc_id in affected_docs])[:100]}_merged.pdf"
         )
-        / f"{'_'.join([str(doc_id) for doc_id in affected_docs])[:100]}_merged.pdf"
-    )
-    merged_pdf.remove_unreferenced_resources()
-    merged_pdf.save(filepath, min_version=version)
-    merged_pdf.close()
+        merger.save(filepath)
 
     if metadata_document_id:
         metadata_document = qs.get(id=metadata_document_id)
@@ -777,64 +750,60 @@ def split(
     )
     doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
     pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
-    import pikepdf
 
     consume_tasks = []
 
     try:
-        with pikepdf.open(pair.source_doc.source_path) as pdf:
-            for idx, split_doc in enumerate(pages):
-                dst: pikepdf.Pdf = pikepdf.new()
-                for page in split_doc:
-                    dst.pages.append(pdf.pages[page - 1])
-                filepath: Path = (
-                    Path(
-                        tempfile.mkdtemp(dir=settings.SCRATCH_DIR),
-                    )
-                    / f"{doc.id}_{split_doc[0]}-{split_doc[-1]}.pdf"
-                )
-                dst.remove_unreferenced_resources()
-                dst.save(filepath)
-                dst.close()
+        outputs = [
+            (
+                [pdf_ops.PageSpec(page) for page in split_doc],
+                partial(_scratch_path, f"{doc.id}_{split_doc[0]}-{split_doc[-1]}.pdf"),
+            )
+            for split_doc in pages
+        ]
+        filepaths = pdf_ops.build_pdfs(pair.source_doc.source_path, outputs)
 
-                overrides: DocumentMetadataOverrides = (
-                    DocumentMetadataOverrides().from_document(doc)
-                )
-                overrides.title = f"{doc.title} (split {idx + 1})"
-                if user is not None:
-                    overrides.owner_id = user.id
-                if not delete_originals:
-                    overrides.skip_asn_if_exists = True
-                logger.info(
-                    f"Adding split document with pages {split_doc} to the task queue.",
-                )
-                consume_tasks.append(
-                    consume_file.s(
-                        input_doc=ConsumableDocument(
-                            source=DocumentSource.ConsumeFolder,
-                            original_file=filepath,
-                        ),
-                        overrides=overrides,
-                    ).set(headers={"trigger_source": trigger_source}),
-                )
+        for idx, (split_doc, filepath) in enumerate(
+            zip(pages, filepaths, strict=True),
+        ):
+            overrides: DocumentMetadataOverrides = (
+                DocumentMetadataOverrides().from_document(doc)
+            )
+            overrides.title = f"{doc.title} (split {idx + 1})"
+            if user is not None:
+                overrides.owner_id = user.id
+            if not delete_originals:
+                overrides.skip_asn_if_exists = True
+            logger.info(
+                f"Adding split document with pages {split_doc} to the task queue.",
+            )
+            consume_tasks.append(
+                consume_file.s(
+                    input_doc=ConsumableDocument(
+                        source=DocumentSource.ConsumeFolder,
+                        original_file=filepath,
+                    ),
+                    overrides=overrides,
+                ).set(headers={"trigger_source": trigger_source}),
+            )
 
-            if delete_originals:
-                backup = release_archive_serial_numbers([doc.id])
-                logger.info(
-                    "Queueing removal of original document after consumption of the split documents",
-                )
-                try:
-                    chord(
-                        header=consume_tasks,
-                        body=delete.si([doc.id]),
-                    ).on_error(
-                        restore_archive_serial_numbers_task.s(backup),
-                    ).apply_async()
-                except Exception:
-                    restore_archive_serial_numbers(backup)
-                    raise
-            else:
-                group(consume_tasks).delay()
+        if delete_originals:
+            backup = release_archive_serial_numbers([doc.id])
+            logger.info(
+                "Queueing removal of original document after consumption of the split documents",
+            )
+            try:
+                chord(
+                    header=consume_tasks,
+                    body=delete.si([doc.id]),
+                ).on_error(
+                    restore_archive_serial_numbers_task.s(backup),
+                ).apply_async()
+            except Exception:
+                restore_archive_serial_numbers(backup)
+                raise
+        else:
+            group(consume_tasks).delay()
 
     except Exception as e:
         logger.exception(f"Error splitting document {doc.id}: {e}")
@@ -855,8 +824,6 @@ def delete_pages(
     )
     doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
     pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
-    pages = sorted(pages)  # sort pages to avoid index issues
-    import pikepdf
 
     try:
         # Produce edited PDF to a temp file and create a new version
@@ -864,13 +831,7 @@ def delete_pages(
             Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
             / f"{pair.root_doc.id}_pages_deleted.pdf"
         )
-        with pikepdf.open(pair.source_doc.source_path) as pdf:
-            offset = 1  # pages are 1-indexed
-            for page_num in pages:
-                pdf.pages.remove(pdf.pages[page_num - offset])
-                offset += 1  # remove() changes the index of the pages
-            pdf.remove_unreferenced_resources()
-            pdf.save(filepath)
+        pdf_ops.remove_pages(pair.source_doc.source_path, filepath, pages)
 
         overrides = DocumentMetadataOverrides().from_document(pair.root_doc)
         if user is not None:
@@ -919,47 +880,28 @@ def edit_pdf(
     )
     doc = Document.objects.select_related("root_document").get(id=doc_ids[0])
     pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
-    import pikepdf
-
-    pdf_docs: list[pikepdf.Pdf] = []
-
     try:
-        if not operations:
-            raise ValueError("Output document index is out of bounds")
-
-        max_idx = max(op.get("doc", 0) for op in operations)
-        if update_document and max_idx > 0:
-            logger.error(
-                "Update requested but multiple output documents specified",
+        output_count = pdf_ops.validate_page_operations(
+            operations,
+            single_output=update_document,
+        )
+        page_specs: list[list[pdf_ops.PageSpec]] = [[] for _ in range(output_count)]
+        for op in operations:
+            page_specs[op.get("doc", 0)].append(
+                pdf_ops.PageSpec(op["page"], op.get("rotate", 0)),
             )
-            raise ValueError("Multiple output documents specified")
-
-        if any(
-            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
-            for op in operations
-        ):
-            raise ValueError("Output document index is out of bounds")
-
-        with pikepdf.open(pair.source_doc.source_path) as src:
-            # prepare output documents
-            pdf_docs = [pikepdf.new() for _ in range(max_idx + 1)]
-
-            for op in operations:
-                dst = pdf_docs[op.get("doc", 0)]
-                page = src.pages[op["page"] - 1]
-                dst.pages.append(page)
-                if op.get("rotate"):
-                    dst.pages[-1].rotate(op["rotate"], relative=True)
 
         if update_document:
             # Create a new version from the edited PDF rather than replacing in-place
-            pdf = pdf_docs[0]
-            pdf.remove_unreferenced_resources()
-            filepath: Path = (
-                Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
-                / f"{pair.root_doc.id}_edited.pdf"
+            (filepath,) = pdf_ops.build_pdfs(
+                pair.source_doc.source_path,
+                [
+                    (
+                        page_specs[0],
+                        partial(_scratch_path, f"{pair.root_doc.id}_edited.pdf"),
+                    ),
+                ],
             )
-            pdf.save(filepath)
             overrides = (
                 DocumentMetadataOverrides().from_document(pair.root_doc)
                 if include_metadata
@@ -980,6 +922,19 @@ def edit_pdf(
                 headers={"trigger_source": trigger_source},
             )
         else:
+            version_filepaths = pdf_ops.build_pdfs(
+                pair.source_doc.source_path,
+                [
+                    (
+                        specs,
+                        partial(
+                            _scratch_path,
+                            f"{pair.root_doc.id}_edit_{idx}.pdf",
+                        ),
+                    )
+                    for idx, specs in enumerate(page_specs, start=1)
+                ],
+            )
             consume_tasks = []
             overrides = (
                 DocumentMetadataOverrides().from_document(pair.root_doc)
@@ -991,15 +946,9 @@ def edit_pdf(
                 overrides.actor_id = user.id
             if not delete_original:
                 overrides.skip_asn_if_exists = True
-            if delete_original and len(pdf_docs) == 1:
+            if delete_original and output_count == 1:
                 overrides.asn = pair.root_doc.archive_serial_number
-            for idx, pdf in enumerate(pdf_docs, start=1):
-                version_filepath: Path = (
-                    Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
-                    / f"{pair.root_doc.id}_edit_{idx}.pdf"
-                )
-                pdf.remove_unreferenced_resources()
-                pdf.save(version_filepath)
+            for version_filepath in version_filepaths:
                 consume_tasks.append(
                     consume_file.s(
                         input_doc=ConsumableDocument(
@@ -1049,8 +998,6 @@ def remove_password(
     """
     Remove password protection from PDF documents.
     """
-    import pikepdf
-
     for doc_id in doc_ids:
         doc = Document.objects.select_related("root_document").get(id=doc_id)
         pair = _resolve_root_and_source_doc(doc, source_mode=source_mode)
@@ -1064,76 +1011,69 @@ def remove_password(
                 doc.id,
                 pair.source_doc.source_path,
             )
-            try:
-                with pikepdf.open(source_path) as pdf:
-                    if not pdf.is_encrypted:
-                        logger.info(
-                            "Skipping password removal for document %s because the "
-                            "source PDF is not encrypted",
-                            pair.root_doc.id,
-                        )
-                        continue
-            except pikepdf.PasswordError:
-                # Password-protected PDFs need the supplied password below.
-                pass
-
-            with pikepdf.open(source_path, password=password) as pdf:
-                filepath: Path = (
-                    Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
-                    / f"{pair.root_doc.id}_unprotected.pdf"
+            if not pdf_ops.needs_decrypt(source_path):
+                logger.info(
+                    "Skipping password removal for document %s because the "
+                    "source PDF is not encrypted",
+                    pair.root_doc.id,
                 )
-                pdf.remove_unreferenced_resources()
-                pdf.save(filepath)
+                continue
 
-                if update_document:
-                    # Create a new version rather than modifying the root/original in place.
-                    overrides = (
-                        DocumentMetadataOverrides().from_document(pair.root_doc)
-                        if include_metadata
-                        else DocumentMetadataOverrides()
-                    )
-                    if user is not None:
-                        overrides.owner_id = user.id
-                        overrides.actor_id = user.id
-                    consume_file.apply_async(
-                        kwargs={
-                            "input_doc": ConsumableDocument(
-                                source=DocumentSource.ConsumeFolder,
-                                original_file=filepath,
-                                root_document_id=pair.root_doc.id,
-                            ),
-                            "overrides": overrides,
-                        },
-                        headers={"trigger_source": trigger_source},
-                    )
+            filepath = pdf_ops.decrypt_pdf(
+                source_path,
+                partial(_scratch_path, f"{pair.root_doc.id}_unprotected.pdf"),
+                password,
+            )
+
+            if update_document:
+                # Create a new version rather than modifying the root/original in place.
+                overrides = (
+                    DocumentMetadataOverrides().from_document(pair.root_doc)
+                    if include_metadata
+                    else DocumentMetadataOverrides()
+                )
+                if user is not None:
+                    overrides.owner_id = user.id
+                    overrides.actor_id = user.id
+                consume_file.apply_async(
+                    kwargs={
+                        "input_doc": ConsumableDocument(
+                            source=DocumentSource.ConsumeFolder,
+                            original_file=filepath,
+                            root_document_id=pair.root_doc.id,
+                        ),
+                        "overrides": overrides,
+                    },
+                    headers={"trigger_source": trigger_source},
+                )
+            else:
+                consume_tasks = []
+                overrides = (
+                    DocumentMetadataOverrides().from_document(pair.root_doc)
+                    if include_metadata
+                    else DocumentMetadataOverrides()
+                )
+                if user is not None:
+                    overrides.owner_id = user.id
+                    overrides.actor_id = user.id
+
+                consume_tasks.append(
+                    consume_file.s(
+                        input_doc=ConsumableDocument(
+                            source=DocumentSource.ConsumeFolder,
+                            original_file=filepath,
+                        ),
+                        overrides=overrides,
+                    ).set(headers={"trigger_source": trigger_source}),
+                )
+
+                if delete_original:
+                    chord(
+                        header=consume_tasks,
+                        body=delete.si([doc.id]),
+                    ).delay()
                 else:
-                    consume_tasks = []
-                    overrides = (
-                        DocumentMetadataOverrides().from_document(pair.root_doc)
-                        if include_metadata
-                        else DocumentMetadataOverrides()
-                    )
-                    if user is not None:
-                        overrides.owner_id = user.id
-                        overrides.actor_id = user.id
-
-                    consume_tasks.append(
-                        consume_file.s(
-                            input_doc=ConsumableDocument(
-                                source=DocumentSource.ConsumeFolder,
-                                original_file=filepath,
-                            ),
-                            overrides=overrides,
-                        ).set(headers={"trigger_source": trigger_source}),
-                    )
-
-                    if delete_original:
-                        chord(
-                            header=consume_tasks,
-                            body=delete.si([doc.id]),
-                        ).delay()
-                    else:
-                        group(consume_tasks).delay()
+                    group(consume_tasks).delay()
 
         except Exception as e:
             logger.exception(

src/documents/filters.py

@@ -50,7 +50,6 @@ from documents.models import ShareLink
 from documents.models import ShareLinkBundle
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.permissions import annotate_authorizing_fields
 from documents.permissions import permitted_document_ids
 from documents.permissions import permitted_object_ids
 from documents.versioning import annotate_effective_content
@@ -1076,9 +1075,6 @@ class PermittedObjectsFilter(BaseFilterBackend):
 
     include_granted: bool = True
     perm_codename: str | None = None
-    # A self-referencing foreign key whose target authorizes a row, so a row is
-    # judged by its parent's owner and grants (``Document.root_document``).
-    parent_field: str | None = None
 
     def filter_queryset(self, request, queryset, view):
         # Before the superuser and owner-only paths, neither of which consults
@@ -1090,23 +1086,11 @@ class PermittedObjectsFilter(BaseFilterBackend):
         if request.user.is_superuser:
             return queryset
         if not self.include_granted:
-            owner_field = "owner"
-            if self.parent_field is not None:
-                queryset = annotate_authorizing_fields(queryset, self.parent_field)
-                owner_field = "authorizing_owner"
-            return queryset.filter(
-                Q(**{owner_field: request.user.pk})
-                | Q(**{f"{owner_field}__isnull": True}),
-            )
+            return queryset.filter(Q(owner=request.user) | Q(owner__isnull=True))
         model = queryset.model
         perm = self.perm_codename or f"view_{model._meta.model_name}"
         return queryset.filter(
-            id__in=permitted_object_ids(
-                request.user,
-                model,
-                perm,
-                parent_field=self.parent_field,
-            ),
+            id__in=permitted_object_ids(request.user, model, perm),
         )
 
 

src/documents/management/commands/document_index.py

@@ -67,22 +67,18 @@ class Command(PaperlessCommand):
                 if options.get("recreate"):
                     wipe_index(settings.INDEX_DIR)
 
-                documents = (
-                    Document.objects.filter(root_document__isnull=True)
-                    .select_related(
-                        "correspondent",
-                        "document_type",
-                        "storage_path",
-                        "owner",
-                    )
-                    .prefetch_related(
-                        "tags",
-                        "notes__user",
-                        "custom_fields__field",
-                        "versions",
-                        "barcodes",
-                        "versions__barcodes",
-                    )
+                documents = Document.objects.select_related(
+                    "correspondent",
+                    "document_type",
+                    "storage_path",
+                    "owner",
+                ).prefetch_related(
+                    "tags",
+                    "notes__user",
+                    "custom_fields__field",
+                    "versions",
+                    "barcodes",
+                    "versions__barcodes",
                 )
                 total = documents.count()
                 rebuild_kwargs = {}

src/documents/pdf_ops.py

@@ -0,0 +1,194 @@
+"""
+Pure PDF page operations used by documents.bulk_edit.
+
+This module deliberately knows nothing about Django, Celery or the documents
+app: callers resolve documents, choose output paths and queue work. Every
+function that writes a PDF removes unreferenced resources before saving.
+
+pikepdf is always called as ``pikepdf.open(...)`` / ``pikepdf.new()`` (never
+``from pikepdf import open``) so tests can patch those module attributes.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+from typing import NamedTuple
+
+import pikepdf
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+    from collections.abc import Iterable
+    from collections.abc import Mapping
+    from collections.abc import Sequence
+    from pathlib import Path
+    from types import TracebackType
+
+
+class PageSpec(NamedTuple):
+    """One page of an output PDF: a 1-indexed source page, optionally rotated."""
+
+    page: int
+    rotate: int = 0  # relative degrees, 0 leaves the page alone
+
+
+def _require_positive(pages: Iterable[int]) -> None:
+    for page in pages:
+        if page < 1:
+            raise ValueError(f"Page numbers start at 1, got {page}")
+
+
+def rotate_pdf(src: Path, dst: Path, degrees: int) -> None:
+    """
+    Rotate every page relatively on the opened document, not a rebuild, so Info,
+    XMP and outlines are kept. ``src`` is not modified.
+    """
+    with pikepdf.open(src) as pdf:
+        for page in pdf.pages:
+            page.rotate(degrees, relative=True)
+        pdf.remove_unreferenced_resources()
+        pdf.save(dst)
+
+
+def remove_pages(src: Path, dst: Path, pages: Iterable[int]) -> None:
+    """
+    Remove 1-indexed pages from the opened document, not a rebuild, so Info, XMP
+    and outlines are kept. ``src`` is not modified.
+
+    Duplicates are ignored. Pages are removed highest first so earlier removals
+    never shift the index of later ones.
+    """
+    unique = sorted(set(pages))
+    _require_positive(unique)
+    with pikepdf.open(src) as pdf:
+        for page_num in reversed(unique):
+            del pdf.pages[page_num - 1]
+        pdf.remove_unreferenced_resources()
+        pdf.save(dst)
+
+
+def build_pdfs(
+    src: Path,
+    outputs: Sequence[tuple[Sequence[PageSpec], Callable[[], Path]]],
+) -> list[Path]:
+    """
+    Build one new PDF per output from pages of ``src``, opening ``src`` once.
+
+    Each output is ``(page_specs, make_dst)``. Every page number is checked against
+    ``src`` before any output is built, and ``make_dst`` is called after that
+    output's pages are copied and immediately before it is saved, so a bad page
+    number in any output never leaves a destination behind. Document-level data
+    (Info, XMP, outlines) is not carried over. Returns the written paths in output
+    order.
+    """
+    for specs, _ in outputs:
+        _require_positive(spec.page for spec in specs)
+
+    written: list[Path] = []
+    with pikepdf.open(src) as source:
+        page_count = len(source.pages)
+        for specs, _ in outputs:
+            for spec in specs:
+                if spec.page > page_count:
+                    raise IndexError(
+                        f"Page {spec.page} is out of range, the PDF has "
+                        f"{page_count} pages",
+                    )
+        for specs, make_dst in outputs:
+            dst = pikepdf.new()
+            for spec in specs:
+                dst.pages.append(source.pages[spec.page - 1])
+                if spec.rotate:
+                    dst.pages[-1].rotate(spec.rotate, relative=True)
+            dst.remove_unreferenced_resources()
+            path = make_dst()
+            dst.save(path)
+            dst.close()
+            written.append(path)
+    return written
+
+
+def validate_page_operations(
+    operations: Sequence[Mapping[str, int]],
+    *,
+    single_output: bool,
+) -> int:
+    """
+    Validate ``edit_pdf`` style operations and return the output document count.
+
+    Each operation has ``page`` and optionally ``rotate`` and ``doc`` (the output
+    document index, default 0). The bounds rule is kept as it was: a ``doc`` index
+    must be below the number of operations.
+    """
+    if not operations:
+        raise ValueError("Output document index is out of bounds")
+
+    max_idx = max(op.get("doc", 0) for op in operations)
+    if single_output and max_idx > 0:
+        raise ValueError("Multiple output documents specified")
+
+    if any(
+        op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations) for op in operations
+    ):
+        raise ValueError("Output document index is out of bounds")
+
+    return max_idx + 1
+
+
+def needs_decrypt(src: Path) -> bool:
+    """
+    True if ``src`` is encrypted. A PDF that needs a password to open at all
+    counts as encrypted.
+    """
+    try:
+        with pikepdf.open(src) as pdf:
+            return bool(pdf.is_encrypted)
+    except pikepdf.PasswordError:
+        return True
+
+
+def decrypt_pdf(src: Path, make_dst: Callable[[], Path], password: str) -> Path:
+    """
+    Write an unencrypted copy of ``src`` and return its path.
+
+    ``make_dst`` is only called once the password has been accepted, so a wrong
+    password never leaves a destination behind.
+    """
+    with pikepdf.open(src, password=password) as pdf:
+        pdf.remove_unreferenced_resources()
+        dst = make_dst()
+        pdf.save(dst)
+    return dst
+
+
+class PdfMerger:
+    """
+    Accumulates the pages of several PDFs into one new PDF.
+
+    ``add`` raises if a source cannot be read; deciding whether to skip it is the
+    caller's policy. Use as a context manager so the merged PDF is closed.
+    """
+
+    def __init__(self) -> None:
+        self._pdf = pikepdf.new()
+        self._version: str = self._pdf.pdf_version
+
+    def __enter__(self) -> PdfMerger:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc: BaseException | None,
+        tb: TracebackType | None,
+    ) -> None:
+        self._pdf.close()
+
+    def add(self, path: Path) -> None:
+        with pikepdf.open(str(path)) as pdf:
+            self._version = max(self._version, pdf.pdf_version)
+            self._pdf.pages.extend(pdf.pages)
+
+    def save(self, dst: Path) -> None:
+        self._pdf.remove_unreferenced_resources()
+        self._pdf.save(dst, min_version=self._version)

src/documents/permissions.py

@@ -6,19 +6,14 @@ from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.contrib.contenttypes.models import ContentType
 from django.db.models import Case
-from django.db.models import CharField
 from django.db.models import Count
-from django.db.models import Exists
-from django.db.models import F
 from django.db.models import IntegerField
 from django.db.models import Model
-from django.db.models import OuterRef
 from django.db.models import Q
 from django.db.models import QuerySet
 from django.db.models import Value
 from django.db.models import When
 from django.db.models.functions import Cast
-from django.db.models.functions import Coalesce
 from guardian.core import ObjectPermissionChecker
 from guardian.models import GroupObjectPermission
 from guardian.models import UserObjectPermission
@@ -30,7 +25,6 @@ from rest_framework.permissions import BasePermission
 from rest_framework.permissions import DjangoObjectPermissions
 
 from documents.models import Document
-from documents.versioning import get_root_document
 
 
 class PaperlessObjectPermissions(DjangoObjectPermissions):
@@ -354,7 +348,6 @@ def permitted_object_ids(
     perm: str,
     *,
     include_deleted: bool = False,
-    parent_field: str | None = None,
 ) -> QuerySet[int]:
     """
     Generic version of ``permitted_document_ids`` for any model with an
@@ -363,20 +356,6 @@ def permitted_object_ids(
     soft-delete pattern (currently only ``Document``); for every other model
     it is accepted but has no effect, since those models have no soft-delete
     concept.
-
-    ``parent_field`` names a self-referencing foreign key whose target
-    authorizes the row (``Document.root_document``). A row with a parent is
-    visible exactly when its parent is, judged by the parent's owner and
-    grants, so the row's own owner and grants are ignored.
-
-    Guardian stores ``object_pk`` as a string, so each grant is an ``EXISTS``
-    keyed on the row's id cast to a string, which can use guardian's
-    (user, permission, object_pk) unique index. Casting every ``object_pk`` to
-    an integer for an ``id IN (...)`` is not indexable, and MariaDB cannot
-    materialize it inside the owner ``OR``, so it re-scans the user's grants
-    for every row. The user's groups are matched with an ``IN`` subquery
-    rather than a join through the membership table, which SQLite plans badly
-    once the grant tables grow.
     """
     has_soft_delete = hasattr(model, "global_objects")
     manager = (
@@ -384,14 +363,8 @@ def permitted_object_ids(
     )
     base_qs = manager.all().only("id", "owner")
 
-    owner_field, key_field = "owner", "pk"
-    if parent_field is not None:
-        owner_field, key_field = "authorizing_owner", "authorizing_id"
-        base_qs = annotate_authorizing_fields(base_qs, parent_field)
-    unowned = Q(**{f"{owner_field}__isnull": True})
-
     if user is None or not getattr(user, "is_authenticated", False):
-        return base_qs.filter(unowned).values_list("id", flat=True)
+        return base_qs.filter(owner__isnull=True).values_list("id", flat=True)
 
     # Deactivated users get nothing, deactivated superusers included, so this
     # has to come before the superuser shortcut. guardian's
@@ -415,50 +388,26 @@ def permitted_object_ids(
         "permission__content_type": content_type,
     }
 
-    key_as_text = Cast(OuterRef(key_field), CharField(max_length=64))
-    granted_to_user = Exists(
-        UserObjectPermission.objects.filter(
-            user=user,
-            object_pk=key_as_text,
-            **perm_filter,
-        ),
+    user_perm_ids = (
+        UserObjectPermission.objects.filter(user=user, **perm_filter)
+        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+        .values_list("object_pk_int", flat=True)
     )
-    granted_to_group = Exists(
-        GroupObjectPermission.objects.filter(
-            group_id__in=user.groups.values("id"),
-            object_pk=key_as_text,
-            **perm_filter,
-        ),
+    group_perm_ids = (
+        GroupObjectPermission.objects.filter(group__user=user, **perm_filter)
+        .annotate(object_pk_int=Cast("object_pk", IntegerField()))
+        .values_list("object_pk_int", flat=True)
     )
+    permitted_ids = user_perm_ids.union(group_perm_ids)
 
     return base_qs.filter(
-        Q(**{owner_field: user.pk}) | unowned | granted_to_user | granted_to_group,
+        Q(owner=user) | Q(owner__isnull=True) | Q(id__in=permitted_ids),
     ).values_list("id", flat=True)
 
 
 ModelT = TypeVar("ModelT", bound=Model)
 
 
-def annotate_authorizing_fields(
-    queryset: QuerySet[ModelT],
-    parent_field: str,
-) -> QuerySet[ModelT]:
-    """
-    Annotate each row with ``authorizing_id`` and ``authorizing_owner``: the id
-    and owner of the row that authorizes it. A row with a parent (the
-    self-referencing foreign key ``parent_field``) is authorized by its parent,
-    any other row by itself.
-    """
-    return queryset.annotate(
-        authorizing_id=Coalesce(f"{parent_field}_id", "id"),
-        authorizing_owner=Case(
-            When(**{f"{parent_field}_id__isnull": True}, then=F("owner_id")),
-            default=F(f"{parent_field}__owner_id"),
-            output_field=IntegerField(),
-        ),
-    )
-
-
 def user_is_unrestricted(user: User | None) -> bool:
     """
     True when ``user`` means "no restriction at all" (an absent user, or an
@@ -521,17 +470,8 @@ def permitted_document_ids(
     ``include_deleted=True`` for callers that need to check permission on
     soft-deleted documents (e.g. trash restore). This intentionally avoids
     ``get_objects_for_user`` to keep the subquery small and index-friendly.
-
-    A version is authorized by its root document, so a version's own owner and
-    grants never matter.
     """
-    return permitted_object_ids(
-        user,
-        Document,
-        perm,
-        include_deleted=include_deleted,
-        parent_field="root_document",
-    )
+    return permitted_object_ids(user, Document, perm, include_deleted=include_deleted)
 
 
 def get_document_count_filter_for_user(user, related_name: str = "documents"):
@@ -690,14 +630,7 @@ def has_perms_owner_aware(user, perms, obj):
     single-object check still has many production callers. Several callers
     remain across ``documents/``, ``paperless_mail/``, and ``paperless_ai/``
     -- grep for this function name before removing it.
-
-    A document version is authorized by its root document, like in
-    ``permitted_document_ids``, so a version's own owner and grants never
-    matter. Fetch the root with ``select_related("root_document__owner")`` to
-    avoid extra queries.
     """
-    if isinstance(obj, Document):
-        obj = get_root_document(obj)
     checker = ObjectPermissionChecker(user)
     return obj.owner is None or obj.owner == user or checker.has_perm(perms, obj)
 

src/documents/search/_backend.py

@@ -7,7 +7,6 @@ import threading
 import time
 from datetime import UTC
 from datetime import datetime
-from datetime import timedelta
 from enum import StrEnum
 from itertools import islice
 from typing import TYPE_CHECKING
@@ -32,7 +31,6 @@ from documents.search._query import parse_user_query
 from documents.search._schema import _write_sentinels
 from documents.search._schema import build_schema
 from documents.search._schema import open_or_rebuild_index
-from documents.search._schema import rebuild_in_progress
 from documents.search._schema import wipe_index
 from documents.search._tokenizer import ascii_fold
 from documents.search._tokenizer import autocomplete_tokens
@@ -56,19 +54,6 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger("paperless.search")
 
-# tantivy stores dates as signed 64-bit nanoseconds since the Unix epoch, which
-# covers 1677-09-21T00:12:43 to 2262-04-11T23:47:16 UTC
-_INDEX_DATE_NANOS_MIN: Final[int] = -(2**63)
-_INDEX_DATE_NANOS_MAX: Final[int] = 2**63 - 1
-_UNIX_EPOCH: Final[datetime] = datetime(1970, 1, 1, tzinfo=UTC)
-
-
-def _is_indexable_date(value: datetime) -> bool:
-    """Whether value, at whole-second precision, fits tantivy's date range."""
-    nanos = ((value - _UNIX_EPOCH) // timedelta(seconds=1)) * 1_000_000_000
-    return _INDEX_DATE_NANOS_MIN <= nanos <= _INDEX_DATE_NANOS_MAX
-
-
 _LOCK_TIMEOUT_SECONDS: Final[float] = 10.0  # per-attempt acquire timeout
 _LOCK_RETRY_ATTEMPTS: Final[int] = 4  # total attempts (1 initial + 3 retries)
 _LOCK_BACKOFF_BASE: Final[float] = 1.0  # seconds
@@ -284,14 +269,9 @@ class WriteBatch:
         and adding the new version. This ensures stale document data (e.g., after
         permission changes) doesn't persist in the index.
 
-        Only root documents are indexed, with their effective content, so a
-        version is indexed as its root document.
-
         Args:
             document: Django Document instance to index
         """
-        if document.root_document_id is not None:
-            document = document.root_document
         self.remove(document.pk)
         doc = self._backend._build_tantivy_doc(document)
         self._writer.add_document(doc)
@@ -316,22 +296,20 @@ class WriteBatch:
         An id with no matching document (e.g. deleted between the caller
         collecting ids and the batch running) is silently skipped, matching
         ``add_or_update()``'s existing single-document deferred-task behavior
-        rather than erroring or leaving a stale index entry. The id of a
-        version stands for its root document.
+        rather than erroring or leaving a stale index entry.
 
         Args:
             ids: Primary keys of Document instances to index
         """
         from documents.models import Document
         from documents.versioning import annotate_effective_content
-        from documents.versioning import root_document_ids
 
         ids = list(ids)
         if not ids:
             return
 
         queryset = annotate_effective_content(
-            Document.objects.filter(pk__in=root_document_ids(ids))
+            Document.objects.filter(pk__in=ids)
             .select_related("correspondent", "document_type", "storage_path", "owner")
             .prefetch_related(
                 "tags",
@@ -649,15 +627,7 @@ class TantivyBackend:
             document.created.day,
             tzinfo=UTC,
         )
-        if _is_indexable_date(created_date):
-            doc.add_date("created", created_date)
-        else:
-            logger.warning(
-                "Document %s has a created date (%s) outside the range the search "
-                "index can store; it will be indexed without a created date",
-                document.pk,
-                document.created,
-            )
+        doc.add_date("created", created_date)
         doc.add_date("modified", document.modified)
         doc.add_date("added", document.added)
 
@@ -1140,44 +1110,39 @@ class TantivyBackend:
                 flushing a segment, deferring merge work; they do not avoid it.
         """
         wipe_index(self._path)
-        # The marker covers the window where the empty index is already stamped
-        # as current but not yet populated, so an interrupted rebuild is retried.
-        with rebuild_in_progress(self._path):
-            new_index = tantivy.Index(build_schema(), path=str(self._path))
-            _write_sentinels(self._path)
-            register_tokenizers(new_index, settings.SEARCH_LANGUAGE)
+        new_index = tantivy.Index(build_schema(), path=str(self._path))
+        _write_sentinels(self._path)
+        register_tokenizers(new_index, settings.SEARCH_LANGUAGE)
 
-            # Point instance at the new index so _build_tantivy_doc uses it
-            old_index, old_schema = self._raw_index, self._raw_schema
-            self._raw_index = new_index
-            self._raw_schema = new_index.schema
-            # Stream documents one-by-one (so the progress bar advances per
-            # document) while fetching viewer permissions one SQL query per
-            # chunk. The stream is Sized, so iter_wrapper can still discover
-            # the total.
-            documents_stream = _DocumentViewerStream(documents, chunk_size=1000)
-            try:
-                writer = new_index.writer(heap_size=writer_heap_bytes)
-                for document, (viewer_ids, viewer_group_ids) in iter_wrapper(
-                    documents_stream,
-                ):
-                    doc = self._build_tantivy_doc(
-                        document,
-                        viewer_ids=viewer_ids,
-                        viewer_group_ids=viewer_group_ids,
-                    )
-                    writer.add_document(doc)
-                writer.commit()
-                # Wait for background merge threads to finish so all segments
-                # are fully merged and persisted before the index is considered
-                # rebuilt.
-                writer.wait_merging_threads()
-                new_index.reload()
-            except BaseException:  # pragma: no cover
-                # Restore old index on failure so the backend remains usable
-                self._raw_index = old_index
-                self._raw_schema = old_schema
-                raise
+        # Point instance at the new index so _build_tantivy_doc uses it
+        old_index, old_schema = self._raw_index, self._raw_schema
+        self._raw_index = new_index
+        self._raw_schema = new_index.schema
+        # Stream documents one-by-one (so the progress bar advances per
+        # document) while fetching viewer permissions one SQL query per chunk.
+        # The stream is Sized, so iter_wrapper can still discover the total.
+        documents_stream = _DocumentViewerStream(documents, chunk_size=1000)
+        try:
+            writer = new_index.writer(heap_size=writer_heap_bytes)
+            for document, (viewer_ids, viewer_group_ids) in iter_wrapper(
+                documents_stream,
+            ):
+                doc = self._build_tantivy_doc(
+                    document,
+                    viewer_ids=viewer_ids,
+                    viewer_group_ids=viewer_group_ids,
+                )
+                writer.add_document(doc)
+            writer.commit()
+            # Wait for background merge threads to finish so all segments are
+            # fully merged and persisted before the index is considered rebuilt.
+            writer.wait_merging_threads()
+            new_index.reload()
+        except BaseException:  # pragma: no cover
+            # Restore old index on failure so the backend remains usable
+            self._raw_index = old_index
+            self._raw_schema = old_schema
+            raise
 
 
 def chunked(iterable, size):

src/documents/search/_schema.py

@@ -4,7 +4,6 @@ import hashlib
 import json
 import logging
 import shutil
-from contextlib import contextmanager
 from typing import TYPE_CHECKING
 from typing import Final
 from typing import NamedTuple
@@ -17,7 +16,6 @@ from whoosh_compat import FieldKind
 from documents.search._fields import PUBLIC_FIELDS
 
 if TYPE_CHECKING:
-    from collections.abc import Iterator
     from pathlib import Path
 
 logger = logging.getLogger("paperless.search")
@@ -30,11 +28,6 @@ logger = logging.getLogger("paperless.search")
 # v3 - barcodes JSON field for stored barcode contents
 SCHEMA_VERSION: Final[int] = 3
 
-# Present in the index directory from the moment a full rebuild starts until it
-# finishes. If a rebuild is interrupted it is left behind, so the half-built
-# index is not mistaken for a complete one.
-REBUILD_MARKER: Final[str] = ".rebuilding"
-
 
 class FieldDescriptor(NamedTuple):
     """One tantivy field, in declaration order.
@@ -262,9 +255,9 @@ def needs_rebuild(index_dir: Path) -> bool:
     """
     Check if the search index needs rebuilding.
 
-    True if a previous full rebuild never finished (the rebuild marker is still
-    present), or if the index's stamped settings no longer match the current
-    configuration. See _settings_mismatch().
+    Reads .index_settings.json to compare the stored schema version, search
+    language and schema fingerprint against the current configuration. Returns
+    True if the file is missing, unparsable, or any value mismatches.
 
     Args:
         index_dir: Path to the search index directory
@@ -272,40 +265,6 @@ def needs_rebuild(index_dir: Path) -> bool:
     Returns:
         True if the index needs rebuilding, False if it's up to date
     """
-    if (index_dir / REBUILD_MARKER).exists():
-        logger.warning("Previous search index rebuild did not finish - rebuilding.")
-        return True
-    return _settings_mismatch(index_dir)
-
-
-@contextmanager
-def rebuild_in_progress(index_dir: Path) -> Iterator[None]:
-    """
-    Flag the index as incomplete for the duration of a full rebuild.
-
-    The marker is cleared only if the block exits cleanly. There is deliberately
-    no try/finally: an exception must leave the marker behind so the next
-    needs_rebuild() check retries the rebuild.
-    """
-    marker = index_dir / REBUILD_MARKER
-    marker.touch()
-    yield
-    marker.unlink(missing_ok=True)
-
-
-def _settings_mismatch(index_dir: Path) -> bool:
-    """
-    Check the stamped settings against the current configuration.
-
-    Reads .index_settings.json to compare the stored schema version, search
-    language and schema fingerprint. Returns True if the file is missing,
-    unparsable, or any value mismatches.
-
-    This deliberately ignores the rebuild marker: open_or_rebuild_index() uses it
-    so that a process opening the index while another process is mid-rebuild
-    (or after one died) does not wipe the partial index out from under it.
-    Repopulating is the job of ``document_index reindex``.
-    """
     settings_file = index_dir / ".index_settings.json"
     if not settings_file.exists():
         return True
@@ -374,7 +333,7 @@ def open_or_rebuild_index(index_dir: Path | None = None) -> tantivy.Index:
         index_dir = cast("Path", settings.INDEX_DIR)
     if not index_dir.exists():
         return tantivy.Index(build_schema())
-    if _settings_mismatch(index_dir):
+    if needs_rebuild(index_dir):
         wipe_index(index_dir)
         idx = tantivy.Index(build_schema(), path=str(index_dir))
         _write_sentinels(index_dir)

src/documents/serialisers.py

@@ -2144,6 +2144,8 @@ class BulkEditSerializer(
             raise serializers.ValidationError("pages must be a list")
         if not all(isinstance(i, int) for i in parameters["pages"]):
             raise serializers.ValidationError("pages must be a list of integers")
+        if any(i < 1 for i in parameters["pages"]):
+            raise serializers.ValidationError("pages must be positive integers")
 
     def _validate_parameters_merge(self, parameters) -> None:
         if "delete_originals" in parameters:

src/documents/tasks.py

@@ -502,8 +502,6 @@ def update_document_content_maybe_archive_file(
                 llm_index_add_or_update_document(document)
 
             clear_document_caches(document.pk)
-            if document.root_document_id is not None:
-                clear_document_caches(document.root_document_id)
 
         except Exception:
             logger.exception(

src/documents/tests/search/test_backend.py

@@ -1,6 +1,4 @@
 import json
-import logging
-from datetime import date
 from pathlib import Path
 
 import pytest
@@ -18,10 +16,7 @@ from documents.search._backend import TantivyBackend
 from documents.search._backend import WriteBatch
 from documents.search._backend import get_backend
 from documents.search._backend import reset_backend
-from documents.search._schema import REBUILD_MARKER
-from documents.search._schema import needs_rebuild
 from documents.signals.handlers import add_to_index
-from paperless_testing.dirs import PaperlessDirs
 from paperless_testing.factories import CorrespondentFactory
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import DocumentTypeFactory
@@ -293,80 +288,6 @@ class TestAddOrUpdateIds:
         assert backend.search_ids("updated", user=None) == [doc.pk]
 
 
-class TestVersionsAreIndexedAsTheirRoot:
-    """Only root documents are indexed, with their effective content, so
-    every write path that is handed a version indexes its root instead."""
-
-    @staticmethod
-    def _root_with_version() -> tuple[Document, Document]:
-        root = DocumentFactory(title="Statement", content="stale text")
-        version = DocumentFactory(
-            title="Statement",
-            content="latest text",
-            root_document=root,
-            version_index=1,
-        )
-        return root, version
-
-    def test_add_or_update_indexes_the_root_of_a_version(
-        self,
-        backend: TantivyBackend,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The version is passed to add_or_update
-        THEN:
-            - The root is indexed with the version's text, and the version is not
-        """
-        root, version = self._root_with_version()
-
-        backend.add_or_update(version)
-
-        assert backend.search_ids("latest", user=None) == [root.pk]
-        assert backend.search_ids("stale", user=None) == []
-
-    def test_add_or_update_ids_indexes_each_root_once(
-        self,
-        backend: TantivyBackend,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - Both ids are passed to add_or_update_ids
-        THEN:
-            - The root is indexed once and the version is not indexed
-        """
-        root, version = self._root_with_version()
-
-        with backend.batch_update() as batch:
-            batch.add_or_update_ids([version.pk, root.pk])
-
-        assert backend.search_ids("Statement", user=None) == [root.pk]
-        assert backend.search_ids("latest", user=None) == [root.pk]
-
-    def test_add_or_update_ids_resolves_a_lone_version(
-        self,
-        backend: TantivyBackend,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - Only the version's id is passed to add_or_update_ids
-        THEN:
-            - The root is indexed
-        """
-        root, version = self._root_with_version()
-
-        with backend.batch_update() as batch:
-            batch.add_or_update_ids([version.pk])
-
-        assert backend.search_ids("latest", user=None) == [root.pk]
-
-
 class TestSearch:
     """Test search query parsing and matching via search_ids."""
 
@@ -902,53 +823,6 @@ class TestRebuild:
         backend.rebuild(Document.objects.all(), iter_wrapper=wrapper)
         assert 30 in seen
 
-    def test_successful_rebuild_leaves_index_up_to_date(
-        self,
-        backend: TantivyBackend,
-        paperless_dirs: PaperlessDirs,
-    ) -> None:
-        """
-        GIVEN:
-            - A backend and one document
-        WHEN:
-            - rebuild() completes
-        THEN:
-            - needs_rebuild() is False and no rebuild marker remains
-        """
-        DocumentFactory.create()
-
-        backend.rebuild(Document.objects.all())
-
-        assert needs_rebuild(paperless_dirs.index_dir) is False
-        assert not (paperless_dirs.index_dir / REBUILD_MARKER).exists()
-
-    def test_interrupted_rebuild_is_retried(
-        self,
-        backend: TantivyBackend,
-        paperless_dirs: PaperlessDirs,
-    ) -> None:
-        """
-        GIVEN:
-            - A rebuild that dies while indexing documents (e.g. the database
-              connection is lost)
-        WHEN:
-            - needs_rebuild() is checked afterwards
-        THEN:
-            - It is True, even though the empty index was already stamped with
-              current settings, so the next start rebuilds instead of reporting
-              the index as up to date
-        """
-        DocumentFactory.create()
-
-        def die(pairs):
-            raise RuntimeError("terminating connection due to administrator command")
-            yield  # pragma: no cover
-
-        with pytest.raises(RuntimeError):
-            backend.rebuild(Document.objects.all(), iter_wrapper=die)
-
-        assert needs_rebuild(paperless_dirs.index_dir) is True
-
     def test_includes_group_granted_viewers(self, backend: TantivyBackend) -> None:
         """Rebuild must index viewer ids for group-only grants, not just direct ones.
 
@@ -980,79 +854,6 @@ class TestRebuild:
         assert ids == [doc.pk]
 
 
-class TestCreatedDateOutOfRange:
-    """The index stores dates as nanosecond i64 values (1677-09-22 to 2262-04-11).
-
-    A document whose created date falls outside that window must not abort
-    indexing: it is indexed without a created value and a warning names it.
-    """
-
-    @pytest.mark.parametrize(
-        ("created", "expected_warnings"),
-        [
-            pytest.param(date(1677, 9, 22), 0, id="first-representable-day"),
-            pytest.param(date(2262, 4, 11), 0, id="last-representable-day"),
-            pytest.param(date(1677, 9, 21), 1, id="day-before-first"),
-            pytest.param(date(2262, 4, 12), 1, id="day-after-last"),
-            pytest.param(date(16, 8, 30), 1, id="two-digit-year-read-as-year-16"),
-            pytest.param(date(9999, 12, 31), 1, id="max-python-date"),
-        ],
-    )
-    def test_add_or_update_indexes_document_and_warns_when_out_of_range(
-        self,
-        backend: TantivyBackend,
-        caplog: pytest.LogCaptureFixture,
-        created: date,
-        expected_warnings: int,
-    ) -> None:
-        """
-        GIVEN:
-            - A document with a created date at or beyond the index date limits
-        WHEN:
-            - The document is added to the index
-        THEN:
-            - The document is indexed and searchable either way
-            - A warning naming the document is logged only for out-of-range dates
-        """
-        doc = DocumentFactory(created=created, content="boundarycontent")
-
-        with caplog.at_level(logging.WARNING, logger="paperless.search"):
-            backend.add_or_update(doc)
-
-        assert backend.search_ids("boundarycontent", user=None) == [doc.pk]
-        warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
-        assert len(warnings) == expected_warnings
-        if expected_warnings:
-            assert f"Document {doc.pk}" in warnings[0].getMessage()
-
-    def test_rebuild_continues_past_out_of_range_document(
-        self,
-        backend: TantivyBackend,
-        caplog: pytest.LogCaptureFixture,
-    ) -> None:
-        """
-        GIVEN:
-            - A document with an unrepresentable created date among valid ones
-        WHEN:
-            - The index is rebuilt
-        THEN:
-            - Rebuild completes and every document is searchable
-            - A warning names the offending document
-        """
-        good = DocumentFactory(created=date(2016, 8, 30), content="rebuildcontent")
-        bad = DocumentFactory(created=date(16, 8, 30), content="rebuildcontent")
-
-        with caplog.at_level(logging.WARNING, logger="paperless.search"):
-            backend.rebuild(Document.objects.all())
-
-        assert sorted(backend.search_ids("rebuildcontent", user=None)) == sorted(
-            [good.pk, bad.pk],
-        )
-        warnings = [r for r in caplog.records if r.levelno == logging.WARNING]
-        assert len(warnings) == 1
-        assert f"Document {bad.pk}" in warnings[0].getMessage()
-
-
 class TestAutocomplete:
     """Test autocomplete functionality."""
 

src/documents/tests/test_api_bulk_edit.py

@@ -1843,6 +1843,36 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         m.assert_called_once()
         self.assertEqual(m.call_args.kwargs["pages"], [[1], [2, 3, 4], [5]])
 
+    @mock.patch("documents.serialisers.bulk_edit.delete_pages")
+    def test_bulk_edit_delete_pages_rejects_pages_below_one(self, m) -> None:
+        """
+        GIVEN:
+            - A legacy delete_pages bulk edit
+        WHEN:
+            - API to bulk edit is called with a page number below 1
+        THEN:
+            - API returns HTTP 400
+            - delete_pages is not called
+        """
+        self.setup_mock(m, "delete_pages")
+
+        for pages in ([0], [-1], [1, 0]):
+            with self.subTest(pages=pages):
+                response = self.client.post(
+                    "/api/documents/bulk_edit/",
+                    json.dumps(
+                        {
+                            "documents": [self.doc2.id],
+                            "method": "delete_pages",
+                            "parameters": {"pages": pages},
+                        },
+                    ),
+                    content_type="application/json",
+                )
+                self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+                self.assertIn(b"pages must be positive integers", response.content)
+        m.assert_not_called()
+
     @mock.patch("documents.views.bulk_edit.rotate")
     def test_rotate_insufficient_permissions(self, m) -> None:
         self.doc1.owner = User.objects.get(username="temp_admin")

src/documents/tests/test_api_document_versions.py

@@ -8,7 +8,6 @@ from auditlog.models import LogEntry  # type: ignore[import-untyped]
 from django.contrib.contenttypes.models import ContentType
 from django.core.files.uploadedfile import SimpleUploadedFile
 from django.test import TestCase as DjangoTestCase
-from django.test import override_settings
 from django.utils import timezone
 from rest_framework import status
 from rest_framework.test import APITestCase
@@ -17,17 +16,13 @@ from documents.data_models import DocumentSource
 from documents.filters import EffectiveContentFilter
 from documents.filters import TitleContentFilter
 from documents.models import Document
-from documents.models import Note
-from documents.models import ShareLink
 from documents.versioning import annotate_effective_content
 from documents.views import DocumentSelectionMixin
 from paperless_testing.dirs import DirectoriesMixin
 from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import UserFactory
 from paperless_testing.http import read_streaming_response
-from paperless_testing.permissions import grant_all_global
 from paperless_testing.permissions import grant_global
-from paperless_testing.permissions import grant_object
 
 if TYPE_CHECKING:
     from pathlib import Path
@@ -1048,152 +1043,3 @@ class TestBulkSelectionExcludesVersions(DjangoTestCase):
         )
 
         self.assertEqual(selected, [root.id])
-
-
-class TestVersionActionPermissions(DirectoriesMixin, APITestCase):
-    def setUp(self):
-        super().setUp()
-        self.user = UserFactory()
-        grant_all_global(self.user)
-        self.client.force_authenticate(self.user)
-        self.root = DocumentFactory(owner=UserFactory())
-        self.version = DocumentFactory(root_document=self.root, owner=None)
-
-    @override_settings(AUDIT_LOG_ENABLED=True)
-    def test_actions_reject_stale_version_ownership(self):
-        note = Note.objects.create(document=self.version, note="Version note")
-        for owner in (None, self.user):
-            self.version.owner = owner
-            self.version.save(update_fields=["owner"])
-            for action in (
-                "notes",
-                "suggestions",
-                "ai_suggestions",
-                "history",
-                "share_links",
-            ):
-                with self.subTest(owner=owner, action=action):
-                    response = self.client.get(
-                        f"/api/documents/{self.version.pk}/{action}/",
-                    )
-                    self.assertEqual(response.status_code, 403)
-            response = self.client.post(
-                f"/api/documents/{self.version.pk}/notes/",
-                {"note": "New note"},
-            )
-            self.assertEqual(response.status_code, 403)
-            response = self.client.delete(
-                f"/api/documents/{self.version.pk}/notes/?id={note.pk}",
-            )
-            self.assertEqual(response.status_code, 403)
-            response = self.client.post(
-                "/api/share_links/",
-                {"document": self.version.pk, "file_version": "original"},
-            )
-            self.assertEqual(response.status_code, 403)
-            response = self.client.post(
-                "/api/share_link_bundles/",
-                {"document_ids": [self.version.pk], "file_version": "original"},
-                format="json",
-            )
-            self.assertEqual(response.status_code, 400)
-            response = self.client.post(
-                "/api/documents/email/",
-                {
-                    "documents": [self.version.pk],
-                    "addresses": "recipient@example.com",
-                    "subject": "Version",
-                    "message": "Version",
-                },
-                format="json",
-            )
-            self.assertEqual(response.status_code, 403)
-            with (
-                mock.patch("documents.views.AIConfig") as ai_config,
-                mock.patch("documents.views.stream_chat_with_documents") as chat,
-            ):
-                ai_config.return_value.ai_enabled = True
-                response = self.client.post(
-                    "/api/documents/chat/",
-                    {"q": "Version?", "document_id": self.version.pk},
-                    format="json",
-                )
-            self.assertEqual(response.status_code, 403)
-            chat.assert_not_called()
-        self.assertTrue(Note.objects.filter(pk=note.pk).exists())
-        self.assertFalse(ShareLink.objects.exists())
-
-    @mock.patch("documents.views.build_share_link_bundle.apply_async")
-    def test_root_permissions_allow_sharing_a_private_version(self, build_mock):
-        self.version.owner = UserFactory()
-        self.version.save(update_fields=["owner"])
-        grant_object(self.user, self.root, "view_document", "change_document")
-        note = Note.objects.create(document=self.version, note="Version note")
-        response = self.client.get(f"/api/documents/{self.version.pk}/notes/")
-        self.assertEqual(response.status_code, 200)
-        self.assertEqual(response.data[0]["id"], note.pk)
-        response = self.client.post(
-            "/api/share_links/",
-            {"document": self.version.pk, "file_version": "original"},
-        )
-        self.assertEqual(response.status_code, 201)
-        self.assertEqual(ShareLink.objects.get().document_id, self.version.pk)
-        response = self.client.get(f"/api/documents/{self.version.pk}/share_links/")
-        self.assertEqual(response.status_code, 200)
-        self.assertEqual(len(response.data), 1)
-        response = self.client.post(
-            "/api/share_link_bundles/",
-            {"document_ids": [self.version.pk], "file_version": "original"},
-            format="json",
-        )
-        self.assertEqual(response.status_code, 201)
-        build_mock.assert_called_once()
-
-    def test_root_view_permission_does_not_allow_note_changes(self):
-        grant_object(self.user, self.root, "view_document")
-        note = Note.objects.create(document=self.version, note="Version note")
-        response = self.client.get(f"/api/documents/{self.version.pk}/notes/")
-        self.assertEqual(response.status_code, 200)
-        response = self.client.post(
-            f"/api/documents/{self.version.pk}/notes/",
-            {"note": "New note"},
-        )
-        self.assertEqual(response.status_code, 403)
-        response = self.client.delete(
-            f"/api/documents/{self.version.pk}/notes/?id={note.pk}",
-        )
-        self.assertEqual(response.status_code, 403)
-        self.assertTrue(Note.objects.filter(pk=note.pk).exists())
-
-    @override_settings(AUDIT_LOG_ENABLED=True)
-    def test_history_uses_root_ownership(self):
-        self.root.owner = self.user
-        self.root.save(update_fields=["owner"])
-        self.version.owner = UserFactory()
-        self.version.save(update_fields=["owner"])
-        response = self.client.get(f"/api/documents/{self.version.pk}/history/")
-        self.assertEqual(response.status_code, 200)
-
-    def test_selection_data_rejects_stale_version_ownership(self):
-        for owner in (None, self.user):
-            self.version.owner = owner
-            self.version.save(update_fields=["owner"])
-            with self.subTest(owner=owner):
-                response = self.client.post(
-                    "/api/documents/selection_data/",
-                    {"documents": [self.version.pk]},
-                    format="json",
-                )
-                self.assertEqual(response.status_code, 403)
-
-    def test_selection_data_allows_private_version_of_permitted_root(self):
-        self.version.owner = UserFactory()
-        self.version.save(update_fields=["owner"])
-        grant_object(self.user, self.root, "view_document")
-        other = DocumentFactory(owner=self.user)
-        response = self.client.post(
-            "/api/documents/selection_data/",
-            {"documents": [self.version.pk, other.pk]},
-            format="json",
-        )
-        self.assertEqual(response.status_code, 200)

src/documents/tests/test_api_search.py

@@ -1196,59 +1196,6 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         self.assertIn(d3.id, result_ids)
         self.assertNotIn(d4.id, result_ids)
 
-    def test_search_more_like_version_uses_its_root(self) -> None:
-        """
-        GIVEN:
-            - A document similar in content to a root document, and one that is not
-            - A version of the root document, which is never indexed
-        WHEN:
-            - API request for more like the version
-        THEN:
-            - The documents similar to the root are returned, not the version
-        """
-        indexed = {}
-        for name, title, content, day in (
-            ("root", "bank statement 1", "things i paid for in august", (2019, 3, 4)),
-            (
-                "similar",
-                "bank statement 3",
-                "things i paid for in september",
-                (2020, 7, 9),
-            ),
-            (
-                "other",
-                "Quarterly Report",
-                "quarterly revenue profit margin",
-                (2021, 11, 30),
-            ),
-        ):
-            with time_machine.travel(
-                timezone.make_aware(datetime.datetime(*day)),
-                tick=False,
-            ):
-                indexed[name] = DocumentFactory(
-                    title=title,
-                    content=content,
-                    created=datetime.date(*day),
-                    added=timezone.make_aware(datetime.datetime(*day)),
-                )
-        version = DocumentFactory(
-            root_document=indexed["root"],
-            version_index=1,
-            content="things i paid for in august",
-        )
-        backend = get_backend()
-        for document in indexed.values():
-            backend.add_or_update(document)
-
-        response = self.client.get(f"/api/documents/?more_like_id={version.id}")
-
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        result_ids = [r["id"] for r in response.data["results"]]
-        self.assertIn(indexed["similar"].id, result_ids)
-        self.assertNotIn(indexed["other"].id, result_ids)
-        self.assertNotIn(version.id, result_ids)
-
     def test_more_like_requires_id_of_existing_document(self) -> None:
         """
         GIVEN:

src/documents/tests/test_api_trash.py

@@ -6,7 +6,6 @@ from rest_framework.test import APITestCase
 
 from documents.models import Document
 from paperless_testing.dirs import DirectoriesMixin
-from paperless_testing.factories import DocumentFactory
 from paperless_testing.factories import UserFactory
 from paperless_testing.permissions import grant_all_global
 
@@ -280,53 +279,3 @@ class TestTrashAPI(DirectoriesMixin, APITestCase):
             Document.objects.filter(root_document=root).values_list("id", flat=True),
             [version.pk for version in versions],
         )
-
-    def test_api_trash_version_follows_root_owner(self) -> None:
-        """
-        GIVEN:
-            - A deleted version of user2's document, owned by nobody
-            - A deleted version of the user's document, owned by user2
-        WHEN:
-            - The user lists the trash and tries to restore or empty the versions
-        THEN:
-            - Only the version of the user's own document is listed
-            - The other version can't be restored or emptied
-            - The version of the user's own document can be restored
-        """
-        user2 = UserFactory(username="user2")
-        other_version = DocumentFactory(
-            root_document=DocumentFactory(owner=user2),
-            version_index=1,
-        )
-        other_version.delete()
-        own_version = DocumentFactory(
-            owner=user2,
-            root_document=DocumentFactory(owner=self.user),
-            version_index=1,
-        )
-        own_version.delete()
-
-        resp = self.client.get("/api/trash/")
-        self.assertEqual(resp.status_code, status.HTTP_200_OK)
-        self.assertEqual(
-            [doc["id"] for doc in resp.data["results"]],
-            [own_version.pk],
-        )
-
-        for action in ("restore", "empty"):
-            with self.subTest(action=action):
-                resp = self.client.post(
-                    "/api/trash/",
-                    {"action": action, "documents": [other_version.pk]},
-                )
-                self.assertEqual(resp.status_code, status.HTTP_403_FORBIDDEN)
-                self.assertTrue(
-                    Document.deleted_objects.filter(pk=other_version.pk).exists(),
-                )
-
-        resp = self.client.post(
-            "/api/trash/",
-            {"action": "restore", "documents": [own_version.pk]},
-        )
-        self.assertEqual(resp.status_code, status.HTTP_200_OK)
-        self.assertTrue(Document.objects.filter(pk=own_version.pk).exists())

src/documents/tests/test_bulk_edit.py

@@ -1,10 +1,9 @@
 import shutil
+from collections.abc import Callable
 from datetime import date
 from pathlib import Path
 from unittest import mock
 
-import pikepdf
-import pytest
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
@@ -13,7 +12,6 @@ from django.test import TestCase
 from django.test.utils import CaptureQueriesContext
 from guardian.shortcuts import get_groups_with_perms
 from guardian.shortcuts import get_users_with_perms
-from pytest_mock import MockerFixture
 
 from documents import bulk_edit
 from documents.models import Correspondent
@@ -23,9 +21,9 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
+from documents.pdf_ops import PageSpec
 from documents.permissions import set_permissions_for_objects
 from paperless_testing.dirs import DirectoriesMixin
-from paperless_testing.factories import DocumentFactory
 from paperless_testing.permissions import grant_object
 
 
@@ -796,16 +794,14 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.img_doc.save()
 
     @staticmethod
-    def mock_password_required_pdf(
-        mock_open: mock.Mock,
-        fake_pdf: mock.Mock,
-    ) -> None:
-        password_context = mock.MagicMock()
-        password_context.__enter__.return_value = fake_pdf
-        mock_open.side_effect = [
-            pikepdf.PasswordError("password required"),
-            password_context,
-        ]
+    def fake_decrypt(
+        src: Path,
+        make_dst: Callable[[], Path],
+        password: str,
+    ) -> Path:
+        dst = make_dst()
+        dst.write_bytes(b"password removed")
+        return dst
 
     @mock.patch("documents.tasks.consume_file.s")
     def test_merge(self, mock_consume_file) -> None:
@@ -850,12 +846,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
         self.assertEqual(result, "OK")
 
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.PdfMerger")
     @mock.patch("documents.tasks.consume_file.s")
     def test_merge_uses_latest_version_source_for_root_selection(
         self,
         mock_consume_file,
-        mock_open_pdf,
+        mock_merger,
     ) -> None:
         version_file = self.dirs.scratch_dir / "sample2_version_merge.pdf"
         shutil.copy(self.doc2.source_path, version_file)
@@ -866,16 +862,14 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             filename=version_file,
             mime_type="application/pdf",
         )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pdf_version = "1.7"
-        fake_pdf.pages = [mock.Mock()]
-        mock_open_pdf.return_value.__enter__.return_value = fake_pdf
+        merger = mock_merger.return_value.__enter__.return_value
+        merger.save.side_effect = lambda dst: shutil.copy(version.source_path, dst)
 
         result = bulk_edit.merge([self.doc2.id])
 
         self.assertEqual(result, "OK")
-        mock_open_pdf.assert_called_once_with(str(version.source_path))
-        mock_consume_file.assert_not_called()
+        merger.add.assert_called_once_with(version.source_path)
+        mock_consume_file.assert_called_once()
 
     @mock.patch("documents.bulk_edit.delete.si")
     @mock.patch("documents.tasks.consume_file.s")
@@ -1037,18 +1031,18 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
     @mock.patch("documents.tasks.consume_file.delay")
-    @mock.patch("pikepdf.open")
-    def test_merge_with_errors(self, mock_open_pdf, mock_consume_file) -> None:
+    @mock.patch("documents.pdf_ops.PdfMerger.add")
+    def test_merge_with_errors(self, mock_add, mock_consume_file) -> None:
         """
         GIVEN:
             - Existing documents
         WHEN:
             - Merge action is called with 2 documents
-            - Error occurs when opening both files
+            - Error occurs when adding both files
         THEN:
             - Consume file should not be called
         """
-        mock_open_pdf.side_effect = Exception("Error opening PDF")
+        mock_add.side_effect = Exception("Error opening PDF")
         doc_ids = [self.doc2.id, self.doc3.id]
 
         with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
@@ -1085,12 +1079,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(result, "OK")
 
     @mock.patch("documents.bulk_edit.group")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.build_pdfs")
     @mock.patch("documents.tasks.consume_file.s")
     def test_split_uses_latest_version_source_for_root_selection(
         self,
         mock_consume_file,
-        mock_open_pdf,
+        mock_build_pdfs,
         mock_group,
     ) -> None:
         version_file = self.dirs.scratch_dir / "sample2_version_split.pdf"
@@ -1102,17 +1096,15 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             filename=version_file,
             mime_type="application/pdf",
         )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        mock_open_pdf.return_value.__enter__.return_value = fake_pdf
+        mock_build_pdfs.return_value = [version.source_path, version.source_path]
         mock_group.return_value.delay.return_value = None
 
         result = bulk_edit.split([self.doc2.id], [[1], [2]])
 
         self.assertEqual(result, "OK")
-        mock_open_pdf.assert_called_once_with(version.source_path)
-        mock_consume_file.assert_not_called()
-        mock_group.return_value.delay.assert_not_called()
+        self.assertEqual(mock_build_pdfs.call_args.args[0], version.source_path)
+        self.assertEqual(mock_consume_file.call_count, 2)
+        mock_group.return_value.delay.assert_called_once()
 
     @mock.patch("documents.bulk_edit.delete.si")
     @mock.patch("documents.tasks.consume_file.s")
@@ -1200,18 +1192,18 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(self.doc2.archive_serial_number, 222)
 
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.Pdf.save")
-    def test_split_with_errors(self, mock_save_pdf, mock_consume_file) -> None:
+    @mock.patch("documents.pdf_ops.build_pdfs")
+    def test_split_with_errors(self, mock_build_pdfs, mock_consume_file) -> None:
         """
         GIVEN:
             - Existing documents
         WHEN:
             - Split action is called with 1 document and 2 page groups
-            - Error occurs when saving the files
+            - Error occurs when building the files
         THEN:
             - Consume file should not be called
         """
-        mock_save_pdf.side_effect = Exception("Error saving PDF")
+        mock_build_pdfs.side_effect = Exception("Error building PDFs")
         doc_ids = [self.doc2.id]
         pages = [[1, 2], [3]]
 
@@ -1246,10 +1238,10 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(result, "OK")
 
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.Pdf.save")
+    @mock.patch("documents.pdf_ops.rotate_pdf")
     def test_rotate_with_error(
         self,
-        mock_pdf_save,
+        mock_rotate_pdf,
         mock_consume_delay,
     ) -> None:
         """
@@ -1257,11 +1249,11 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             - Existing documents
         WHEN:
             - Rotate action is called with 2 documents
-            - PikePDF raises an error
+            - Rotating the PDF raises an error
         THEN:
             - Rotate action should be called 0 times
         """
-        mock_pdf_save.side_effect = Exception("Error saving PDF")
+        mock_rotate_pdf.side_effect = Exception("Error rotating PDF")
         doc_ids = [self.doc2.id, self.doc3.id]
 
         with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
@@ -1296,10 +1288,10 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.rotate_pdf")
     def test_rotate_explicit_selection_uses_root_source_when_root_selected(
         self,
-        mock_open,
+        mock_rotate_pdf,
         mock_consume_delay,
         mock_magic,
     ) -> None:
@@ -1308,9 +1300,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             title="B version 1",
             root_document=self.doc2,
         )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
 
         result = bulk_edit.rotate(
             [self.doc2.id],
@@ -1319,26 +1308,35 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
+        self.assertEqual(mock_rotate_pdf.call_args.args[0], self.doc2.source_path)
         mock_consume_delay.assert_called_once()
 
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.Pdf.save")
+    @mock.patch("documents.pdf_ops.remove_pages")
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
-    def test_delete_pages(self, mock_magic, mock_pdf_save, mock_consume_delay) -> None:
+    def test_delete_pages(
+        self,
+        mock_magic,
+        mock_remove_pages,
+        mock_consume_delay,
+    ) -> None:
         """
         GIVEN:
             - Existing documents
         WHEN:
             - Delete pages action is called with 1 document and 2 pages
         THEN:
-            - Save should be called once
+            - The pages are removed from the document's source PDF
             - A new version should be enqueued via consume_file
         """
         doc_ids = [self.doc2.id]
         pages = [1, 3]
         result = bulk_edit.delete_pages(doc_ids, pages)
-        mock_pdf_save.assert_called_once()
+        mock_remove_pages.assert_called_once_with(
+            self.doc2.source_path,
+            mock.ANY,
+            [1, 3],
+        )
         mock_consume_delay.assert_called_once()
         task_kwargs = mock_consume_delay.call_args.kwargs["kwargs"]
         self.assertEqual(task_kwargs["input_doc"].root_document_id, self.doc2.id)
@@ -1350,10 +1348,10 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.remove_pages")
     def test_delete_pages_explicit_selection_uses_root_source_when_root_selected(
         self,
-        mock_open,
+        mock_remove_pages,
         mock_consume_delay,
         mock_magic,
     ) -> None:
@@ -1362,9 +1360,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             title="B version 1",
             root_document=self.doc2,
         )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
 
         result = bulk_edit.delete_pages(
             [self.doc2.id],
@@ -1373,23 +1368,26 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
+        self.assertEqual(mock_remove_pages.call_args.args[0], self.doc2.source_path)
         mock_consume_delay.assert_called_once()
 
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.Pdf.save")
-    def test_delete_pages_with_error(self, mock_pdf_save, mock_consume_delay) -> None:
+    @mock.patch("documents.pdf_ops.remove_pages")
+    def test_delete_pages_with_error(
+        self,
+        mock_remove_pages,
+        mock_consume_delay,
+    ) -> None:
         """
         GIVEN:
             - Existing documents
         WHEN:
             - Delete pages action is called with 1 document and 2 pages
-            - PikePDF raises an error
+            - Removing the pages raises an error
         THEN:
-            - Save should be called once
             - No new version should be enqueued
         """
-        mock_pdf_save.side_effect = Exception("Error saving PDF")
+        mock_remove_pages.side_effect = Exception("Error removing pages")
         doc_ids = [self.doc2.id]
         pages = [1, 3]
 
@@ -1419,6 +1417,41 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(result, "OK")
         mock_group.return_value.delay.assert_called_once()
 
+    @mock.patch("documents.bulk_edit.group")
+    @mock.patch("documents.pdf_ops.build_pdfs")
+    @mock.patch("documents.tasks.consume_file.s")
+    def test_edit_pdf_maps_operations_to_outputs(
+        self,
+        mock_consume_file: mock.Mock,
+        mock_build_pdfs: mock.Mock,
+        mock_group: mock.Mock,
+    ) -> None:
+        """
+        GIVEN:
+            - Existing document
+        WHEN:
+            - edit_pdf is called with operations interleaved across two outputs,
+              some of them rotated
+        THEN:
+            - Each output is built from its own operations, in operation order,
+              with the requested rotation
+        """
+        mock_build_pdfs.return_value = [self.doc2.source_path, self.doc2.source_path]
+        mock_group.return_value.delay.return_value = None
+        operations = [
+            {"page": 3, "doc": 1},
+            {"page": 1, "doc": 0, "rotate": 90},
+            {"page": 2, "doc": 1, "rotate": 180},
+        ]
+
+        bulk_edit.edit_pdf([self.doc2.id], operations)
+
+        outputs = mock_build_pdfs.call_args.args[1]
+        self.assertEqual(
+            [specs for specs, _ in outputs],
+            [[PageSpec(1, 90)], [PageSpec(3), PageSpec(2, 180)]],
+        )
+
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
     def test_edit_pdf_with_user_override(self, mock_consume_file, mock_group) -> None:
@@ -1534,12 +1567,10 @@ class TestPDFActions(DirectoriesMixin, TestCase):
 
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.new")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.build_pdfs")
     def test_edit_pdf_explicit_selection_uses_root_source_when_root_selected(
         self,
-        mock_open,
-        mock_new,
+        mock_build_pdfs,
         mock_consume_delay,
         mock_magic,
     ) -> None:
@@ -1548,12 +1579,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             title="B version 1",
             root_document=self.doc2,
         )
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock()]
-        mock_open.return_value.__enter__.return_value = fake_pdf
-        output_pdf = mock.MagicMock()
-        output_pdf.pages = []
-        mock_new.return_value = output_pdf
+        mock_build_pdfs.return_value = [Path("edited.pdf")]
 
         result = bulk_edit.edit_pdf(
             [self.doc2.id],
@@ -1563,7 +1589,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(self.doc2.source_path)
+        self.assertEqual(mock_build_pdfs.call_args.args[0], self.doc2.source_path)
         mock_consume_delay.assert_called_once()
 
     @mock.patch("documents.bulk_edit.group")
@@ -1589,31 +1615,6 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(result, "OK")
         mock_group.return_value.delay.assert_called_once()
 
-    @mock.patch("documents.bulk_edit.group")
-    @mock.patch("documents.tasks.consume_file.s")
-    def test_edit_pdf_open_failure(
-        self,
-        mock_consume_file: mock.Mock,
-        mock_group: mock.Mock,
-    ) -> None:
-        """
-        GIVEN:
-            - Existing document
-        WHEN:
-            - edit_pdf fails to open PDF
-        THEN:
-            - Task group is not called
-        """
-        doc_ids = [self.doc2.id]
-        operations = [
-            {"page": 9999},  # invalid page, forces error during PDF load
-        ]
-        with self.assertLogs("paperless.bulk_edit", level="ERROR"):
-            with self.assertRaises(Exception):
-                bulk_edit.edit_pdf(doc_ids, operations)
-        mock_group.assert_not_called()
-        mock_consume_file.assert_not_called()
-
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
     def test_edit_pdf_multiple_outputs_with_update_flag_errors(
@@ -1640,23 +1641,15 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         mock_group.assert_not_called()
         mock_consume_file.assert_not_called()
 
-    @mock.patch("pikepdf.open")
-    def test_edit_pdf_rejects_invalid_operations(self, mock_open) -> None:
-        for operations in ([], [{"page": 1, "doc": 2**32}]):
-            with self.subTest(operations=operations):
-                with self.assertLogs("paperless.bulk_edit", level="ERROR"):
-                    with self.assertRaisesRegex(ValueError, "index is out of bounds"):
-                        bulk_edit.edit_pdf([self.doc2.id], operations)
-
-        mock_open.assert_not_called()
-
     @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file.delay")
     @mock.patch("documents.tasks.consume_file.apply_async")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
     def test_remove_password_update_document(
         self,
-        mock_open,
+        mock_needs_decrypt,
+        mock_decrypt,
         mock_mkdtemp,
         mock_consume_delay,
         mock_update_document,
@@ -1665,16 +1658,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         temp_dir = self.dirs.scratch_dir / "remove-password-update"
         temp_dir.mkdir(parents=True, exist_ok=True)
         mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock(), mock.Mock()]
-        fake_pdf.is_encrypted = True
-
-        def save_side_effect(target_path):
-            Path(target_path).write_bytes(b"new pdf content")
-
-        fake_pdf.save.side_effect = save_side_effect
-        mock_open.return_value.__enter__.return_value = fake_pdf
+        mock_decrypt.side_effect = self.fake_decrypt
 
         result = bulk_edit.remove_password(
             [doc.id],
@@ -1683,14 +1667,8 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        self.assertEqual(
-            mock_open.call_args_list,
-            [
-                mock.call(doc.source_path),
-                mock.call(doc.source_path, password="secret"),
-            ],
-        )
-        fake_pdf.remove_unreferenced_resources.assert_called_once()
+        mock_needs_decrypt.assert_called_once_with(doc.source_path)
+        mock_decrypt.assert_called_once_with(doc.source_path, mock.ANY, "secret")
         mock_update_document.assert_not_called()
         mock_consume_delay.assert_called_once()
         task_kwargs = mock_consume_delay.call_args.kwargs["kwargs"]
@@ -1703,40 +1681,15 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertEqual(task_kwargs["input_doc"].root_document_id, doc.id)
         self.assertIsNotNone(task_kwargs["overrides"])
 
-    @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
-    def test_remove_password_update_document_skips_unencrypted_pdf(
-        self,
-        mock_open,
-        mock_mkdtemp,
-        mock_consume_delay,
-    ) -> None:
-        doc = self.doc1
-        fake_pdf = mock.MagicMock()
-        fake_pdf.is_encrypted = False
-        mock_open.return_value.__enter__.return_value = fake_pdf
-
-        result = bulk_edit.remove_password(
-            [doc.id],
-            password="secret",
-            update_document=True,
-        )
-
-        self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(doc.source_path)
-        fake_pdf.remove_unreferenced_resources.assert_not_called()
-        fake_pdf.save.assert_not_called()
-        mock_mkdtemp.assert_not_called()
-        mock_consume_delay.assert_not_called()
-
     @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file.delay")
     @mock.patch("documents.tasks.consume_file.apply_async")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
     def test_remove_password_update_document_uses_source_paths(
         self,
-        mock_open,
+        mock_needs_decrypt,
+        mock_decrypt,
         mock_mkdtemp,
         mock_consume_delay,
         mock_update_document,
@@ -1747,14 +1700,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         temp_dir = self.dirs.scratch_dir / "remove-password-source-file"
         temp_dir.mkdir(parents=True, exist_ok=True)
         mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        self.mock_password_required_pdf(mock_open, fake_pdf)
-
-        def save_side_effect(target_path):
-            Path(target_path).write_bytes(b"new pdf content")
-
-        fake_pdf.save.side_effect = save_side_effect
+        mock_decrypt.side_effect = self.fake_decrypt
 
         result = bulk_edit.remove_password(
             [doc.id],
@@ -1764,22 +1710,19 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        self.assertEqual(
-            mock_open.call_args_list,
-            [
-                mock.call(source_file),
-                mock.call(source_file, password="secret"),
-            ],
-        )
+        mock_needs_decrypt.assert_called_once_with(source_file)
+        mock_decrypt.assert_called_once_with(source_file, mock.ANY, "secret")
         mock_update_document.assert_not_called()
         mock_consume_delay.assert_called_once()
 
     @mock.patch("documents.data_models.magic.from_file", return_value="application/pdf")
     @mock.patch("documents.tasks.consume_file.apply_async")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
     def test_remove_password_explicit_selection_uses_root_source_when_root_selected(
         self,
-        mock_open,
+        mock_needs_decrypt,
+        mock_decrypt,
         mock_consume_delay,
         mock_magic,
     ) -> None:
@@ -1788,8 +1731,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             title="A version 1",
             root_document=self.doc1,
         )
-        fake_pdf = mock.MagicMock()
-        self.mock_password_required_pdf(mock_open, fake_pdf)
+        mock_decrypt.return_value = Path("unprotected.pdf")
 
         result = bulk_edit.remove_password(
             [self.doc1.id],
@@ -1799,12 +1741,11 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        self.assertEqual(
-            mock_open.call_args_list,
-            [
-                mock.call(self.doc1.source_path),
-                mock.call(self.doc1.source_path, password="secret"),
-            ],
+        mock_needs_decrypt.assert_called_once_with(self.doc1.source_path)
+        mock_decrypt.assert_called_once_with(
+            self.doc1.source_path,
+            mock.ANY,
+            "secret",
         )
         mock_consume_delay.assert_called_once()
 
@@ -1812,10 +1753,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
     def test_remove_password_creates_consumable_document(
         self,
-        mock_open: mock.Mock,
+        mock_needs_decrypt: mock.Mock,
+        mock_decrypt: mock.Mock,
         mock_mkdtemp: mock.Mock,
         mock_consume_file: mock.Mock,
         mock_group: mock.Mock,
@@ -1825,15 +1768,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         temp_dir = self.dirs.scratch_dir / "remove-password"
         temp_dir.mkdir(parents=True, exist_ok=True)
         mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        self.mock_password_required_pdf(mock_open, fake_pdf)
-
-        def save_side_effect(target_path: Path) -> None:
-            target_path.write_bytes(b"password removed")
-
-        fake_pdf.save.side_effect = save_side_effect
+        mock_decrypt.side_effect = self.fake_decrypt
         mock_group.return_value.delay.return_value = None
 
         user = User.objects.create(username="owner")
@@ -1848,13 +1783,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        self.assertEqual(
-            mock_open.call_args_list,
-            [
-                mock.call(doc.source_path),
-                mock.call(doc.source_path, password="secret"),
-            ],
-        )
+        mock_decrypt.assert_called_once_with(doc.source_path, mock.ANY, "secret")
         mock_consume_file.assert_called_once()
         call_kwargs = mock_consume_file.call_args.kwargs
         consumable_document = call_kwargs["input_doc"]
@@ -1876,21 +1805,18 @@ class TestPDFActions(DirectoriesMixin, TestCase):
     @mock.patch("documents.bulk_edit.chord")
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
-    @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=False)
     def test_remove_password_skips_unencrypted_pdf_without_queueing(
         self,
-        mock_open: mock.Mock,
-        mock_mkdtemp: mock.Mock,
+        mock_needs_decrypt: mock.Mock,
+        mock_decrypt: mock.Mock,
         mock_consume_file: mock.Mock,
         mock_group: mock.Mock,
         mock_chord: mock.Mock,
         mock_delete: mock.Mock,
     ) -> None:
         doc = self.doc2
-        fake_pdf = mock.MagicMock()
-        fake_pdf.is_encrypted = False
-        mock_open.return_value.__enter__.return_value = fake_pdf
 
         result = bulk_edit.remove_password(
             [doc.id],
@@ -1900,10 +1826,8 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        mock_open.assert_called_once_with(doc.source_path)
-        fake_pdf.remove_unreferenced_resources.assert_not_called()
-        fake_pdf.save.assert_not_called()
-        mock_mkdtemp.assert_not_called()
+        mock_needs_decrypt.assert_called_once_with(doc.source_path)
+        mock_decrypt.assert_not_called()
         mock_consume_file.assert_not_called()
         mock_group.assert_not_called()
         mock_chord.assert_not_called()
@@ -1914,10 +1838,12 @@ class TestPDFActions(DirectoriesMixin, TestCase):
     @mock.patch("documents.bulk_edit.group")
     @mock.patch("documents.tasks.consume_file.s")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")
-    @mock.patch("pikepdf.open")
+    @mock.patch("documents.pdf_ops.decrypt_pdf")
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
     def test_remove_password_deletes_original(
         self,
-        mock_open: mock.Mock,
+        mock_needs_decrypt: mock.Mock,
+        mock_decrypt: mock.Mock,
         mock_mkdtemp: mock.Mock,
         mock_consume_file: mock.Mock,
         mock_group: mock.Mock,
@@ -1928,15 +1854,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         temp_dir = self.dirs.scratch_dir / "remove-password-delete"
         temp_dir.mkdir(parents=True, exist_ok=True)
         mock_mkdtemp.return_value = str(temp_dir)
-
-        fake_pdf = mock.MagicMock()
-        fake_pdf.pages = [mock.Mock(), mock.Mock()]
-        self.mock_password_required_pdf(mock_open, fake_pdf)
-
-        def save_side_effect(target_path: Path) -> None:
-            target_path.write_bytes(b"password removed")
-
-        fake_pdf.save.side_effect = save_side_effect
+        mock_decrypt.side_effect = self.fake_decrypt
         mock_chord.return_value.delay.return_value = None
 
         result = bulk_edit.remove_password(
@@ -1948,23 +1866,23 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         )
 
         self.assertEqual(result, "OK")
-        self.assertEqual(
-            mock_open.call_args_list,
-            [
-                mock.call(doc.source_path),
-                mock.call(doc.source_path, password="secret"),
-            ],
-        )
+        mock_decrypt.assert_called_once_with(doc.source_path, mock.ANY, "secret")
         mock_consume_file.assert_called_once()
         mock_group.assert_not_called()
         mock_chord.assert_called_once()
         mock_chord.return_value.delay.assert_called_once()
         mock_delete.si.assert_called_once_with([doc.id])
 
-    @mock.patch("pikepdf.open")
-    def test_remove_password_open_failure(self, mock_open: mock.Mock) -> None:
-        mock_open.side_effect = RuntimeError("wrong password")
-
+    @mock.patch(
+        "documents.pdf_ops.decrypt_pdf",
+        side_effect=RuntimeError("wrong password"),
+    )
+    @mock.patch("documents.pdf_ops.needs_decrypt", return_value=True)
+    def test_remove_password_failure_raises_value_error(
+        self,
+        mock_needs_decrypt: mock.Mock,
+        mock_decrypt: mock.Mock,
+    ) -> None:
         with self.assertLogs("paperless.bulk_edit", level="ERROR") as cm:
             with self.assertRaises(ValueError) as exc:
                 bulk_edit.remove_password([self.doc1.id], password="secret")
@@ -1973,22 +1891,18 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         self.assertIn("Error removing password from document", cm.output[0])
 
 
-@pytest.mark.django_db
-class TestBulkEditReprocess:
-    @pytest.fixture
-    def mock_task(self, mocker: MockerFixture) -> mock.MagicMock:
-        return mocker.patch(
-            "documents.bulk_edit.update_document_content_maybe_archive_file",
+class TestBulkEditReprocess(DirectoriesMixin, TestCase):
+    def setUp(self) -> None:
+        super().setUp()
+
+        self.doc = Document.objects.create(
+            title="test",
+            checksum="A",
+            mime_type="application/pdf",
         )
 
-    @staticmethod
-    def _queued_ids(mock_task: mock.MagicMock) -> list[int]:
-        return [
-            call.kwargs["kwargs"]["document_id"]
-            for call in mock_task.apply_async.call_args_list
-        ]
-
-    def test_reprocess_defaults_to_local(self, mock_task: mock.MagicMock) -> None:
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_defaults_to_local(self, mock_task: mock.Mock) -> None:
         """
         GIVEN:
             - A reprocess request that says nothing about remote OCR
@@ -1997,17 +1911,18 @@ class TestBulkEditReprocess:
         THEN:
             - The task is queued without asking for the remote engine
         """
-        doc = DocumentFactory()
-
-        assert bulk_edit.reprocess([doc.id]) == "OK"
+        result = bulk_edit.reprocess([self.doc.id])
 
+        self.assertEqual(result, "OK")
         mock_task.apply_async.assert_called_once()
-        assert mock_task.apply_async.call_args.kwargs["kwargs"] == {
-            "document_id": doc.id,
-            "remote_ocr": False,
-        }
+        _, kwargs = mock_task.apply_async.call_args
+        self.assertEqual(
+            kwargs["kwargs"],
+            {"document_id": self.doc.id, "remote_ocr": False},
+        )
 
-    def test_reprocess_passes_remote_ocr(self, mock_task: mock.MagicMock) -> None:
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_passes_remote_ocr(self, mock_task: mock.Mock) -> None:
         """
         GIVEN:
             - A reprocess request that explicitly asks for remote OCR
@@ -2016,72 +1931,14 @@ class TestBulkEditReprocess:
         THEN:
             - The request is forwarded to the task for every document
         """
-        docs = DocumentFactory.create_batch(2)
-
-        bulk_edit.reprocess([doc.id for doc in docs], remote_ocr=True)
-
-        assert mock_task.apply_async.call_count == 2
-        for call in mock_task.apply_async.call_args_list:
-            assert call.kwargs["kwargs"]["remote_ocr"]
-
-    def test_reprocess_root_uses_latest_version(
-        self,
-        mock_task: mock.MagicMock,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with two versions
-        WHEN:
-            - reprocess is called with the root document
-        THEN:
-            - The latest version is reprocessed, not the root's original file
-        """
-        root = DocumentFactory()
-        DocumentFactory(root_document=root, version_index=1)
-        latest = DocumentFactory(root_document=root, version_index=2)
-
-        bulk_edit.reprocess([root.id])
-
-        assert self._queued_ids(mock_task) == [latest.id]
-
-    def test_reprocess_explicit_version(self, mock_task: mock.MagicMock) -> None:
-        """
-        GIVEN:
-            - A root document with two versions
-        WHEN:
-            - reprocess is called with the older version
-        THEN:
-            - That version is reprocessed
-        """
-        root = DocumentFactory()
-        older = DocumentFactory(root_document=root, version_index=1)
-        DocumentFactory(root_document=root, version_index=2)
-
-        bulk_edit.reprocess([older.id])
-
-        assert self._queued_ids(mock_task) == [older.id]
-
-    def test_reprocess_root_and_latest_version_dispatches_once(
-        self,
-        mock_task: mock.MagicMock,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with two versions, the latest created on a
-              different date than the root
-        WHEN:
-            - reprocess is called with both the root and its latest version
-        THEN:
-            - The latest version is reprocessed only once
-        """
-        root = DocumentFactory(created=date(2024, 1, 1))
-        DocumentFactory(root_document=root, version_index=1)
-        latest = DocumentFactory(
-            root_document=root,
-            version_index=2,
-            created=date(2025, 1, 1),
+        other = Document.objects.create(
+            title="test2",
+            checksum="B",
+            mime_type="application/pdf",
         )
 
-        bulk_edit.reprocess([root.id, latest.id])
+        bulk_edit.reprocess([self.doc.id, other.id], remote_ocr=True)
 
-        assert self._queued_ids(mock_task) == [latest.id]
+        self.assertEqual(mock_task.apply_async.call_count, 2)
+        for call in mock_task.apply_async.call_args_list:
+            self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])

src/documents/tests/test_management.py

@@ -22,7 +22,6 @@ from documents.models import Document
 from documents.tasks import update_document_content_maybe_archive_file
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
-from paperless_testing.factories import DocumentFactory
 
 sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
@@ -117,27 +116,6 @@ class TestMakeIndex:
         call_command("document_index", "reindex", skip_checks=True)
         mock_get_backend.return_value.rebuild.assert_called_once()
 
-    def test_reindex_skips_versions(self, mocker: MockerFixture) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The reindex command runs
-        THEN:
-            - Only the root document is handed to the rebuild, since a version
-              is indexed as its root
-        """
-        root = DocumentFactory()
-        DocumentFactory(root_document=root, version_index=1)
-        mock_get_backend = mocker.patch(
-            "documents.management.commands.document_index.get_backend",
-        )
-
-        call_command("document_index", "reindex", skip_checks=True)
-
-        documents = mock_get_backend.return_value.rebuild.call_args.args[0]
-        assert list(documents.values_list("pk", flat=True)) == [root.pk]
-
     def test_optimize(self) -> None:
         """Optimize command must execute without error (Tantivy handles optimization automatically)."""
         call_command("document_index", "optimize", skip_checks=True)

src/documents/tests/test_pdf_ops.py

@@ -0,0 +1,520 @@
+"""
+Tests for documents.pdf_ops.
+
+These use real PDFs from the sample directories. No database, Celery or mocks.
+Pages are compared by a hash of their content stream, so page identity and order
+are easy to assert.
+"""
+
+import hashlib
+from collections.abc import Callable
+from pathlib import Path
+
+import pikepdf
+import pytest
+
+from documents import pdf_ops
+from documents.pdf_ops import PageSpec
+
+SRC_ROOT = Path(__file__).parents[2]
+SAMPLES = Path(__file__).parent / "samples"
+THREE_PAGES = SAMPLES / "documents" / "originals" / "0000002.pdf"
+TWELVE_PAGES = SAMPLES / "barcodes" / "split-by-asn-2.pdf"
+ENCRYPTED = SAMPLES / "password-is-test.pdf"
+SIGNED = SRC_ROOT / "paperless" / "tests" / "samples" / "tesseract" / "signed.pdf"
+
+
+def _page_fingerprint(page: pikepdf.Page) -> str:
+    contents = page.obj.get("/Contents")
+    assert contents is not None, "sample page has no /Contents"
+    streams = list(contents) if isinstance(contents, pikepdf.Array) else [contents]
+    return hashlib.sha256(b"".join(s.read_bytes() for s in streams)).hexdigest()
+
+
+def fingerprints(path: Path) -> list[str]:
+    with pikepdf.open(path) as pdf:
+        return [_page_fingerprint(page) for page in pdf.pages]
+
+
+def rotations(path: Path) -> list[int]:
+    with pikepdf.open(path) as pdf:
+        return [int(page.obj.get("/Rotate", 0)) for page in pdf.pages]
+
+
+def docinfo_keys(path: Path) -> set[str]:
+    with pikepdf.open(path) as pdf:
+        return set(pdf.docinfo.keys())
+
+
+def constant(path: Path) -> Callable[[], Path]:
+    return lambda: path
+
+
+@pytest.fixture
+def source_fingerprints() -> list[str]:
+    fps = fingerprints(THREE_PAGES)
+    assert len(set(fps)) == 3, "sample must have three distinct pages"
+    return fps
+
+
+class TestRotatePdf:
+    def test_rotation_is_relative_and_applies_to_every_page(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - It is rotated by 90 degrees, then the result is rotated by 90 again
+        THEN:
+            - Every page is rotated relative to its current rotation
+            - The page content itself is unchanged
+        """
+        once = tmp_path / "once.pdf"
+        twice = tmp_path / "twice.pdf"
+
+        pdf_ops.rotate_pdf(THREE_PAGES, once, 90)
+        pdf_ops.rotate_pdf(once, twice, 90)
+
+        assert rotations(once) == [90, 90, 90]
+        assert rotations(twice) == [180, 180, 180]
+        assert fingerprints(twice) == fingerprints(THREE_PAGES)
+
+    def test_keeps_document_info(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A PDF with document info
+        WHEN:
+            - It is rotated
+        THEN:
+            - The document info is still present in the output
+        """
+        dst = tmp_path / "out.pdf"
+
+        pdf_ops.rotate_pdf(THREE_PAGES, dst, 90)
+
+        assert "/Creator" in docinfo_keys(dst)
+
+
+class TestRemovePages:
+    @pytest.mark.parametrize(
+        ("pages", "kept"),
+        [
+            pytest.param([2], [0, 2], id="single"),
+            pytest.param([3, 1], [1], id="unordered"),
+            pytest.param([2, 2], [0, 2], id="duplicates-remove-once"),
+            pytest.param([], [0, 1, 2], id="empty-keeps-everything"),
+            pytest.param([1, 2, 3], [], id="every-page"),
+        ],
+    )
+    def test_removes_only_the_requested_pages(
+        self,
+        tmp_path: Path,
+        source_fingerprints: list[str],
+        pages: list[int],
+        kept: list[int],
+    ) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - Pages are removed, in any order and possibly repeated
+        THEN:
+            - Exactly the other pages remain, in their original order
+        """
+        dst = tmp_path / "out.pdf"
+
+        pdf_ops.remove_pages(THREE_PAGES, dst, pages)
+
+        assert fingerprints(dst) == [source_fingerprints[i] for i in kept]
+
+    def test_keeps_document_info(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A PDF with document info
+        WHEN:
+            - A page is removed
+        THEN:
+            - The document info is still present in the output
+        """
+        dst = tmp_path / "out.pdf"
+
+        pdf_ops.remove_pages(THREE_PAGES, dst, [1])
+
+        assert "/Creator" in docinfo_keys(dst)
+
+    @pytest.mark.parametrize(
+        "bad_page",
+        [
+            pytest.param(0, id="zero"),
+            pytest.param(-1, id="negative"),
+        ],
+    )
+    def test_rejects_pages_below_one(self, tmp_path: Path, bad_page: int) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - Pages are removed and one of them is below 1
+        THEN:
+            - ValueError is raised
+            - No output file is written
+        """
+        dst = tmp_path / "out.pdf"
+
+        with pytest.raises(ValueError, match="start at 1"):
+            pdf_ops.remove_pages(THREE_PAGES, dst, [1, bad_page])
+
+        assert not dst.exists()
+
+
+class TestBuildPdfs:
+    def test_selects_and_orders_pages(
+        self,
+        tmp_path: Path,
+        source_fingerprints: list[str],
+    ) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - One output is built from pages 3 then 1
+        THEN:
+            - The output has those pages in that order
+            - Its path is returned
+        """
+        dst = tmp_path / "out.pdf"
+
+        written = pdf_ops.build_pdfs(
+            THREE_PAGES,
+            [([PageSpec(3), PageSpec(1)], constant(dst))],
+        )
+
+        assert written == [dst]
+        assert fingerprints(dst) == [source_fingerprints[2], source_fingerprints[0]]
+
+    def test_rotates_only_the_requested_pages(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - One output is built with a different rotation on each page
+        THEN:
+            - Each output page has exactly the rotation requested for it
+        """
+        dst = tmp_path / "out.pdf"
+
+        pdf_ops.build_pdfs(
+            THREE_PAGES,
+            [([PageSpec(1), PageSpec(2, 90), PageSpec(3, 180)], constant(dst))],
+        )
+
+        assert rotations(dst) == [0, 90, 180]
+
+    def test_writes_one_file_per_output_in_order(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A twelve page PDF
+        WHEN:
+            - Two outputs are built from different page ranges
+        THEN:
+            - Two files are written and returned in output order
+            - Each holds exactly its own pages
+        """
+        first = tmp_path / "first.pdf"
+        second = tmp_path / "second.pdf"
+        source = fingerprints(TWELVE_PAGES)
+
+        written = pdf_ops.build_pdfs(
+            TWELVE_PAGES,
+            [
+                ([PageSpec(p) for p in (1, 2, 3)], constant(first)),
+                ([PageSpec(p) for p in range(4, 13)], constant(second)),
+            ],
+        )
+
+        assert written == [first, second]
+        assert fingerprints(first) == source[:3]
+        assert fingerprints(second) == source[3:]
+
+    def test_empty_page_list_writes_a_zero_page_file(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - An output with no pages is built
+        THEN:
+            - A PDF with zero pages is written
+        """
+        dst = tmp_path / "out.pdf"
+
+        pdf_ops.build_pdfs(THREE_PAGES, [([], constant(dst))])
+
+        assert fingerprints(dst) == []
+
+    def test_destination_is_not_requested_when_a_page_is_out_of_range(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - Several outputs are built
+            - A later output refers to a page past the end
+        THEN:
+            - IndexError is raised
+            - No destination was requested for any output, including earlier valid ones
+        """
+        requested: list[Path] = []
+
+        def make_dst() -> Path:
+            requested.append(tmp_path / "out.pdf")
+            return requested[-1]
+
+        with pytest.raises(IndexError):
+            pdf_ops.build_pdfs(
+                THREE_PAGES,
+                [([PageSpec(1)], make_dst), ([PageSpec(99)], make_dst)],
+            )
+
+        assert requested == []
+
+    @pytest.mark.parametrize(
+        "bad_page",
+        [
+            pytest.param(0, id="zero"),
+            pytest.param(-1, id="negative"),
+        ],
+    )
+    def test_rejects_pages_below_one_before_opening_anything(
+        self,
+        tmp_path: Path,
+        bad_page: int,
+    ) -> None:
+        """
+        GIVEN:
+            - A three page PDF
+        WHEN:
+            - Several outputs are built and a later one has a page below 1
+        THEN:
+            - ValueError is raised
+            - No destination was requested for any output
+        """
+        requested: list[Path] = []
+
+        def make_dst() -> Path:
+            requested.append(tmp_path / "out.pdf")
+            return requested[-1]
+
+        with pytest.raises(ValueError, match="start at 1"):
+            pdf_ops.build_pdfs(
+                THREE_PAGES,
+                [([PageSpec(1)], make_dst), ([PageSpec(bad_page)], make_dst)],
+            )
+
+        assert requested == []
+
+
+class TestValidatePageOperations:
+    def test_returns_the_output_count(self) -> None:
+        """
+        GIVEN:
+            - Operations that all target the default output
+        WHEN:
+            - They are validated
+        THEN:
+            - One output document is reported
+        """
+        operations = [{"page": 1}, {"page": 2}, {"page": 3}]
+
+        assert pdf_ops.validate_page_operations(operations, single_output=True) == 1
+
+    def test_gap_in_output_indices_counts_up_to_the_highest(self) -> None:
+        """
+        GIVEN:
+            - Operations that target outputs 0 and 2 but never 1
+        WHEN:
+            - They are validated
+        THEN:
+            - Three output documents are reported
+        """
+        operations = [
+            {"page": 1, "doc": 0},
+            {"page": 2, "doc": 2},
+            {"page": 3, "doc": 0},
+        ]
+
+        count = pdf_ops.validate_page_operations(operations, single_output=False)
+
+        assert count == 3
+
+    def test_empty_operations_are_rejected(self) -> None:
+        """
+        GIVEN:
+            - No operations
+        WHEN:
+            - They are validated
+        THEN:
+            - ValueError is raised
+        """
+        with pytest.raises(ValueError, match="index is out of bounds"):
+            pdf_ops.validate_page_operations([], single_output=False)
+
+    def test_multiple_outputs_rejected_when_single_output_required(self) -> None:
+        """
+        GIVEN:
+            - Operations that target two outputs
+        WHEN:
+            - They are validated with a single output required
+        THEN:
+            - ValueError is raised
+        """
+        operations = [{"page": 1, "doc": 0}, {"page": 2, "doc": 1}]
+
+        with pytest.raises(ValueError, match="Multiple output documents"):
+            pdf_ops.validate_page_operations(operations, single_output=True)
+
+    @pytest.mark.parametrize(
+        "doc",
+        [
+            pytest.param(-1, id="negative"),
+            pytest.param(2, id="equal-to-operation-count"),
+            pytest.param(2**32, id="huge"),
+        ],
+    )
+    def test_output_index_out_of_bounds(self, doc: int) -> None:
+        """
+        GIVEN:
+            - Two operations, one with an output index that is out of bounds
+        WHEN:
+            - They are validated
+        THEN:
+            - ValueError is raised
+        """
+        operations = [{"page": 1, "doc": 0}, {"page": 2, "doc": doc}]
+
+        with pytest.raises(ValueError, match="index is out of bounds"):
+            pdf_ops.validate_page_operations(operations, single_output=False)
+
+
+class TestDecrypt:
+    @pytest.mark.parametrize(
+        ("path", "expected"),
+        [
+            pytest.param(ENCRYPTED, True, id="password-required"),
+            pytest.param(SIGNED, True, id="opens-without-password-but-encrypted"),
+            pytest.param(THREE_PAGES, False, id="not-encrypted"),
+        ],
+    )
+    def test_needs_decrypt(self, path: Path, *, expected: bool) -> None:
+        """
+        GIVEN:
+            - A PDF that is encrypted, or encrypted but openable, or plain
+        WHEN:
+            - needs_decrypt is asked about it
+        THEN:
+            - Only the unencrypted PDF reports False
+        """
+        assert pdf_ops.needs_decrypt(path) is expected
+
+    def test_decrypt_writes_an_unencrypted_copy(self, tmp_path: Path) -> None:
+        """
+        GIVEN:
+            - A password protected PDF
+        WHEN:
+            - It is decrypted with the correct password
+        THEN:
+            - The path from make_dst is returned
+            - The written copy no longer needs decrypting
+        """
+        dst = tmp_path / "out.pdf"
+
+        result = pdf_ops.decrypt_pdf(ENCRYPTED, constant(dst), "test")
+
+        assert result == dst
+        assert pdf_ops.needs_decrypt(dst) is False
+
+    def test_wrong_password_raises_and_never_requests_a_destination(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A password protected PDF
+        WHEN:
+            - It is decrypted with the wrong password
+        THEN:
+            - PasswordError is raised
+            - No destination was requested
+        """
+        requested: list[Path] = []
+
+        def make_dst() -> Path:
+            requested.append(tmp_path / "out.pdf")
+            return requested[-1]
+
+        with pytest.raises(pikepdf.PasswordError):
+            pdf_ops.decrypt_pdf(ENCRYPTED, make_dst, "wrong")
+
+        assert requested == []
+
+
+class TestPdfMerger:
+    def test_pages_are_appended_in_the_order_added(
+        self,
+        tmp_path: Path,
+        source_fingerprints: list[str],
+    ) -> None:
+        """
+        GIVEN:
+            - A reordered PDF and the original three page PDF
+        WHEN:
+            - Both are added to a merger in that order and saved
+        THEN:
+            - The output holds all pages in the order they were added
+        """
+        reordered = tmp_path / "reordered.pdf"
+        merged = tmp_path / "merged.pdf"
+        pdf_ops.build_pdfs(
+            THREE_PAGES,
+            [([PageSpec(3), PageSpec(1)], constant(reordered))],
+        )
+
+        with pdf_ops.PdfMerger() as merger:
+            merger.add(reordered)
+            merger.add(THREE_PAGES)
+            merger.save(merged)
+
+        assert fingerprints(merged) == [
+            source_fingerprints[2],
+            source_fingerprints[0],
+            *source_fingerprints,
+        ]
+
+    def test_output_version_is_at_least_the_highest_source_version(
+        self,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - Two PDFs with different PDF versions
+        WHEN:
+            - Both are added to a merger and saved
+        THEN:
+            - The output version is at least the highest source version
+        """
+        merged = tmp_path / "merged.pdf"
+        with pikepdf.open(TWELVE_PAGES) as pdf:
+            source_versions = [pdf.pdf_version]
+        with pikepdf.open(THREE_PAGES) as pdf:
+            source_versions.append(pdf.pdf_version)
+
+        with pdf_ops.PdfMerger() as merger:
+            merger.add(TWELVE_PAGES)
+            merger.add(THREE_PAGES)
+            merger.save(merged)
+
+        with pikepdf.open(merged) as pdf:
+            assert pdf.pdf_version >= max(source_versions)

src/documents/tests/test_permission_filtering_security.py

@@ -18,7 +18,6 @@ from documents.models import Correspondent
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.permissions import has_perms_owner_aware
 from documents.permissions import permitted_document_ids
 from documents.permissions import permitted_object_ids
 from documents.permissions import restrict_queryset_to_visible
@@ -33,8 +32,6 @@ from paperless_testing.permissions import grant_global
 from paperless_testing.permissions import grant_object
 
 if TYPE_CHECKING:
-    from django.contrib.auth.models import User
-
     from paperless_testing.dirs import PaperlessDirs
 
 
@@ -181,382 +178,6 @@ class TestPermittedDocumentIdsIncludeDeleted:
         )
 
 
-@pytest.mark.django_db
-class TestPermittedDocumentIdsVersions:
-    """
-    A version is authorized by its root document: the version's own owner and
-    grants never matter.
-    """
-
-    @pytest.mark.parametrize(
-        ("root_owner", "version_owner", "expected_visible"),
-        [
-            pytest.param(
-                "other",
-                "nobody",
-                False,
-                id="unowned-version-of-private-root",
-            ),
-            pytest.param("other", "user", False, id="own-version-of-private-root"),
-            pytest.param("user", "other", True, id="foreign-version-of-own-root"),
-            pytest.param("user", "nobody", True, id="unowned-version-of-own-root"),
-            pytest.param("nobody", "other", True, id="private-version-of-unowned-root"),
-        ],
-    )
-    def test_version_follows_root_owner(
-        self,
-        root_owner: str,
-        version_owner: str,
-        *,
-        expected_visible: bool,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document and a version with differing owners
-        WHEN:
-            - The permitted document ids are resolved for the user
-        THEN:
-            - The version is visible exactly when its root is
-        """
-        user = UserFactory()
-        owners = {"user": user, "other": UserFactory(), "nobody": None}
-        root = DocumentFactory(owner=owners[root_owner])
-        version = DocumentFactory(root_document=root, owner=owners[version_owner])
-
-        visible = set(permitted_document_ids(user))
-
-        assert (version.pk in visible) is expected_visible
-        assert (root.pk in visible) is expected_visible
-
-    @staticmethod
-    def grantee(user: User, kind: str) -> User | Group:
-        """The user itself, or a new group the user belongs to."""
-        if kind == "user":
-            return user
-        group = Group.objects.create(name="shared")
-        user.groups.add(group)
-        return group
-
-    @pytest.mark.parametrize(
-        "grantee_kind",
-        [pytest.param("user", id="user"), pytest.param("group", id="group")],
-    )
-    def test_grant_on_root_applies_to_version(self, grantee_kind: str) -> None:
-        """
-        GIVEN:
-            - A private root document shared with a user or one of their groups
-            - A version of it owned by someone else
-        WHEN:
-            - The permitted document ids are resolved for the user
-        THEN:
-            - Both the root and the version are visible
-            - A user without the grant sees neither
-        """
-        user = UserFactory()
-        stranger = UserFactory()
-        root = DocumentFactory(owner=UserFactory())
-        version = DocumentFactory(root_document=root, owner=UserFactory())
-        grant_object(self.grantee(user, grantee_kind), root, "view_document")
-
-        assert_visible_document_ids(
-            permitted_document_ids(user),
-            expected_visible=[root.pk, version.pk],
-            expected_hidden=[],
-        )
-        assert_visible_document_ids(
-            permitted_document_ids(stranger),
-            expected_visible=[],
-            expected_hidden=[root.pk, version.pk],
-        )
-
-    @pytest.mark.parametrize(
-        "grantee_kind",
-        [pytest.param("user", id="user"), pytest.param("group", id="group")],
-    )
-    def test_grant_on_version_is_ignored(self, grantee_kind: str) -> None:
-        """
-        GIVEN:
-            - A private root document
-            - A version with an explicit grant for the user or one of their groups
-        WHEN:
-            - The permitted document ids are resolved for the user
-        THEN:
-            - Neither the root nor the version is visible
-        """
-        user = UserFactory()
-        root = DocumentFactory(owner=UserFactory())
-        version = DocumentFactory(root_document=root, owner=UserFactory())
-        grant_object(self.grantee(user, grantee_kind), version, "view_document")
-
-        assert_visible_document_ids(
-            permitted_document_ids(user),
-            expected_visible=[],
-            expected_hidden=[root.pk, version.pk],
-        )
-
-    def test_grant_on_one_root_does_not_reach_another_roots_version(self) -> None:
-        """
-        GIVEN:
-            - Two private roots, each with a version
-            - The user may view only the first root
-        WHEN:
-            - The permitted document ids are resolved for the user
-        THEN:
-            - Only the first root and its version are visible
-        """
-        user = UserFactory()
-        first = DocumentFactory(owner=UserFactory())
-        first_version = DocumentFactory(root_document=first, owner=UserFactory())
-        second = DocumentFactory(owner=UserFactory())
-        second_version = DocumentFactory(root_document=second, owner=user)
-        grant_object(user, first, "view_document")
-
-        assert_visible_document_ids(
-            permitted_document_ids(user),
-            expected_visible=[first.pk, first_version.pk],
-            expected_hidden=[second.pk, second_version.pk],
-        )
-
-    def test_user_in_several_groups(self) -> None:
-        """
-        GIVEN:
-            - A user in two groups
-            - Two private roots shared with one group each, and a third shared with nobody
-            - A version of each root
-        WHEN:
-            - The permitted document ids are resolved for the user
-        THEN:
-            - The two shared roots and their versions are visible
-            - The third root and its version are not
-        """
-        user = UserFactory()
-        groups = [Group.objects.create(name=f"group{i}") for i in range(2)]
-        user.groups.add(*groups)
-        shared = [DocumentFactory(owner=UserFactory()) for _ in groups]
-        for root, group in zip(shared, groups, strict=True):
-            grant_object(group, root, "view_document")
-        unshared = DocumentFactory(owner=UserFactory())
-        shared_versions = [
-            DocumentFactory(root_document=root, owner=UserFactory()) for root in shared
-        ]
-        unshared_version = DocumentFactory(root_document=unshared, owner=None)
-
-        assert_visible_document_ids(
-            permitted_document_ids(user),
-            expected_visible=[
-                *(root.pk for root in shared),
-                *(version.pk for version in shared_versions),
-            ],
-            expected_hidden=[unshared.pk, unshared_version.pk],
-        )
-
-    def test_permission_is_resolved_through_the_root(self) -> None:
-        """
-        GIVEN:
-            - A private root document where the user may view and change
-        WHEN:
-            - The permitted ids are resolved for view, change and delete
-        THEN:
-            - The version is visible for view and change only
-        """
-        user = UserFactory()
-        root = DocumentFactory(owner=UserFactory())
-        version = DocumentFactory(root_document=root, owner=UserFactory())
-        grant_object(user, root, "view_document", "change_document")
-
-        assert version.pk in set(permitted_document_ids(user))
-        assert version.pk in set(permitted_document_ids(user, perm="change_document"))
-        assert version.pk in set(
-            permitted_document_ids(user, perm="documents.change_document"),
-        )
-        assert version.pk not in set(
-            permitted_document_ids(user, perm="delete_document"),
-        )
-
-    def test_anonymous_sees_versions_of_unowned_roots_only(self) -> None:
-        """
-        GIVEN:
-            - A version owned by nobody under a private root
-            - A version owned by someone under an unowned root
-        WHEN:
-            - The permitted document ids are resolved for an anonymous user
-        THEN:
-            - Only the version of the unowned root is visible
-        """
-        private_root = DocumentFactory(owner=UserFactory())
-        private_version = DocumentFactory(root_document=private_root, owner=None)
-        open_root = DocumentFactory(owner=None)
-        open_version = DocumentFactory(root_document=open_root, owner=UserFactory())
-
-        assert_visible_document_ids(
-            permitted_document_ids(AnonymousUser()),
-            expected_visible=[open_root.pk, open_version.pk],
-            expected_hidden=[private_root.pk, private_version.pk],
-        )
-
-    def test_deleted_versions_follow_their_deleted_root(self) -> None:
-        """
-        GIVEN:
-            - A soft-deleted root document and its version, which deleting the
-              root soft-deletes too; the version is owned by someone else
-        WHEN:
-            - The permitted document ids are resolved with and without deleted
-              documents
-        THEN:
-            - Nothing is visible by default
-            - With deleted documents included, the version is visible to the
-              root's owner and not to the version's own owner
-        """
-        owner = UserFactory()
-        version_owner = UserFactory()
-        root = DocumentFactory(owner=owner)
-        version = DocumentFactory(root_document=root, owner=version_owner)
-        root.delete()
-
-        assert not {root.pk, version.pk} & set(permitted_document_ids(owner))
-        assert_visible_document_ids(
-            permitted_document_ids(owner, include_deleted=True),
-            expected_visible=[root.pk, version.pk],
-            expected_hidden=[],
-        )
-        assert_visible_document_ids(
-            permitted_document_ids(version_owner, include_deleted=True),
-            expected_visible=[],
-            expected_hidden=[root.pk, version.pk],
-        )
-
-    @pytest.mark.parametrize(
-        "is_superuser",
-        [
-            pytest.param(False, id="regular-user"),
-            pytest.param(True, id="superuser"),
-        ],
-    )
-    def test_inactive_user_sees_no_versions(self, *, is_superuser: bool) -> None:
-        """
-        GIVEN:
-            - An inactive user, possibly a superuser, who owns a root and its version
-        WHEN:
-            - The permitted document ids are resolved for them
-        THEN:
-            - Nothing is visible
-        """
-        user = UserFactory(is_active=False, is_superuser=is_superuser)
-        root = DocumentFactory(owner=user)
-        version = DocumentFactory(root_document=root, owner=user)
-
-        assert_visible_document_ids(
-            permitted_document_ids(user),
-            expected_visible=[],
-            expected_hidden=[root.pk, version.pk],
-        )
-
-    def test_superuser_sees_all_versions(self) -> None:
-        """
-        GIVEN:
-            - A private root owned by someone else, with a version
-        WHEN:
-            - The permitted document ids are resolved for a superuser
-        THEN:
-            - Both the root and the version are visible
-        """
-        superuser = UserFactory(superuser=True)
-        root = DocumentFactory(owner=UserFactory())
-        version = DocumentFactory(root_document=root, owner=UserFactory())
-
-        assert_visible_document_ids(
-            permitted_document_ids(superuser),
-            expected_visible=[root.pk, version.pk],
-            expected_hidden=[],
-        )
-
-
-@pytest.mark.django_db
-class TestHasPermsOwnerAwareVersions:
-    """
-    The single-object check agrees with permitted_document_ids: a version is
-    authorized by its root document.
-    """
-
-    @pytest.mark.parametrize(
-        ("root_owner", "version_owner", "expected"),
-        [
-            pytest.param(
-                "other",
-                "nobody",
-                False,
-                id="unowned-version-of-private-root",
-            ),
-            pytest.param("other", "user", False, id="own-version-of-private-root"),
-            pytest.param("user", "other", True, id="foreign-version-of-own-root"),
-            pytest.param("nobody", "other", True, id="private-version-of-unowned-root"),
-        ],
-    )
-    def test_version_follows_root_owner(
-        self,
-        root_owner: str,
-        version_owner: str,
-        *,
-        expected: bool,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document and a version with differing owners
-        WHEN:
-            - The single-object check runs for the version
-        THEN:
-            - The version is allowed exactly when its root is
-        """
-        user = UserFactory()
-        owners = {"user": user, "other": UserFactory(), "nobody": None}
-        root = DocumentFactory(owner=owners[root_owner])
-        version = DocumentFactory(root_document=root, owner=owners[version_owner])
-
-        assert has_perms_owner_aware(user, "view_document", version) is expected
-        assert has_perms_owner_aware(user, "view_document", root) is expected
-
-    def test_grant_on_root_applies_and_grant_on_version_does_not(self) -> None:
-        """
-        GIVEN:
-            - A private root with a version, and a second private root with a version
-            - The user may change only the first root, and was granted the second
-              root's version directly
-        WHEN:
-            - The single-object check runs for each version
-        THEN:
-            - Only the first root's version is allowed
-        """
-        user = UserFactory()
-        shared_root = DocumentFactory(owner=UserFactory())
-        shared_version = DocumentFactory(root_document=shared_root, owner=UserFactory())
-        private_root = DocumentFactory(owner=UserFactory())
-        private_version = DocumentFactory(
-            root_document=private_root,
-            owner=UserFactory(),
-        )
-        grant_object(user, shared_root, "change_document")
-        grant_object(user, private_version, "change_document")
-
-        assert has_perms_owner_aware(user, "change_document", shared_version)
-        assert not has_perms_owner_aware(user, "change_document", private_version)
-
-    def test_other_models_use_their_own_owner(self) -> None:
-        """
-        GIVEN:
-            - A tag owned by someone else, and one owned by the user
-        WHEN:
-            - The single-object check runs for each
-        THEN:
-            - Only the user's own tag is allowed without a grant
-        """
-        user = UserFactory()
-        mine = TagFactory(owner=user)
-        theirs = TagFactory(owner=UserFactory())
-
-        assert has_perms_owner_aware(user, "view_tag", mine)
-        assert not has_perms_owner_aware(user, "view_tag", theirs)
-
-
 @pytest.mark.django_db
 class TestAiChatAllDocumentsPermissionBoundary:
     """

src/documents/tests/test_share_link_bundles.py

@@ -90,13 +90,10 @@ class ShareLinkBundleAPITests(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn("document_ids", response.data)
 
-    def test_create_bundle_rejects_insufficient_permissions(self) -> None:
-        requester = UserFactory(username="bundle_creator")
-        grant_global(requester, "add_sharelinkbundle", "view_document")
-        self.client.force_authenticate(requester)
-        document = DocumentFactory(owner=UserFactory(username="document_owner"))
+    @mock.patch("documents.views.permitted_document_ids", return_value=set())
+    def test_create_bundle_rejects_insufficient_permissions(self, perms_mock) -> None:
         payload = {
-            "document_ids": [self.document.pk, document.pk],
+            "document_ids": [self.document.pk],
             "file_version": ShareLink.FileVersion.ARCHIVE,
             "expiration_days": 7,
         }
@@ -104,8 +101,8 @@ class ShareLinkBundleAPITests(DirectoriesMixin, APITestCase):
         response = self.client.post(self.ENDPOINT, payload, format="json")
 
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn(str(document.pk), str(response.data["document_ids"]))
-        self.assertFalse(ShareLinkBundle.objects.exists())
+        self.assertIn("document_ids", response.data)
+        perms_mock.assert_called()
 
     @mock.patch("documents.views.build_share_link_bundle.apply_async")
     def test_rebuild_bundle_resets_state(self, delay_mock) -> None:

src/documents/tests/test_tasks.py

@@ -20,7 +20,6 @@ from documents.sanity_checker import SanityCheckMessages
 from documents.tests.helpers import dummy_preprocess
 from paperless_testing.assertions import FileSystemAssertsMixin
 from paperless_testing.dirs import DirectoriesMixin
-from paperless_testing.factories import DocumentFactory
 
 
 @pytest.mark.django_db
@@ -288,80 +287,6 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         tasks.update_document_content_maybe_archive_file(doc.pk)
         self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
 
-    def _create_root_with_version(self) -> tuple[Document, Document]:
-        sample1 = self.dirs.scratch_dir / "sample.pdf"
-        shutil.copy(
-            Path(__file__).parent
-            / "samples"
-            / "documents"
-            / "originals"
-            / "0000001.pdf",
-            sample1,
-        )
-        root = DocumentFactory(content="root content", mime_type="application/pdf")
-        version = DocumentFactory(
-            content="my document",
-            filename=sample1,
-            mime_type="application/pdf",
-            root_document=root,
-            version_index=1,
-        )
-        return root, version
-
-    @mock.patch("documents.tasks.clear_document_caches")
-    @mock.patch("documents.search.get_backend")
-    def test_update_content_version_clears_caches_for_root(
-        self,
-        mock_get_backend: mock.Mock,
-        mock_clear_caches: mock.Mock,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - Update content task is called for the version
-        THEN:
-            - The version's content is updated, not the root's
-            - The document is indexed
-            - Caches are cleared for both
-        """
-        root, version = self._create_root_with_version()
-
-        tasks.update_document_content_maybe_archive_file(version.pk)
-
-        self.assertNotEqual(
-            Document.objects.get(pk=version.pk).content,
-            "my document",
-        )
-        self.assertEqual(Document.objects.get(pk=root.pk).content, "root content")
-        mock_get_backend.return_value.add_or_update.assert_called_once()
-        mock_clear_caches.assert_has_calls(
-            [mock.call(version.pk), mock.call(root.pk)],
-        )
-
-    @override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="huggingface")
-    @mock.patch("documents.tasks.llm_index_add_or_update_document")
-    @mock.patch("documents.search.get_backend")
-    def test_update_content_version_updates_llm_index(
-        self,
-        mock_get_backend: mock.Mock,
-        mock_llm_index: mock.Mock,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-            - The LLM index is enabled
-        WHEN:
-            - Update content task is called for the version
-        THEN:
-            - The LLM index is updated
-        """
-        _, version = self._create_root_with_version()
-
-        tasks.update_document_content_maybe_archive_file(version.pk)
-
-        mock_llm_index.assert_called_once()
-
 
 class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
     """

src/documents/versioning.py

@@ -17,26 +17,9 @@ from django.db.models.functions import RowNumber
 from documents.models import Document
 
 if TYPE_CHECKING:
-    from collections.abc import Iterable
-
     from rest_framework.request import Request
 
 
-def root_document_ids(ids: Iterable[int]) -> QuerySet[int]:
-    """
-    The ids of the root documents of the given documents: a root stands for
-    itself and a version for its root. Only the indexes' bookkeeping needs
-    this, since they hold root documents only.
-    """
-    return (
-        Document.objects.filter(pk__in=ids)
-        .annotate(root_id=Coalesce("root_document_id", "id"))
-        .order_by()
-        .values_list("root_id", flat=True)
-        .distinct()
-    )
-
-
 def versions_newest_first(documents: QuerySet[Document]) -> QuerySet[Document]:
     """
     Sorts versions so the newest one comes first using version_index and not on id,

src/documents/views.py

@@ -329,10 +329,9 @@ def _get_tantivy_query_and_mode(params):
 def _get_more_like_id(query_params: dict[str, Any], user: User | None) -> int:
     try:
         more_like_doc_id = int(query_params["more_like_id"])
-        more_like_doc = Document.objects.select_related(
-            "owner",
-            "root_document__owner",
-        ).get(pk=more_like_doc_id)
+        more_like_doc = Document.objects.select_related("owner").get(
+            pk=more_like_doc_id,
+        )
     except (TypeError, ValueError, Document.DoesNotExist):
         raise PermissionDenied(_("Invalid more_like_id"))
 
@@ -343,8 +342,7 @@ def _get_more_like_id(query_params: dict[str, Any], user: User | None) -> int:
     ):
         raise PermissionDenied(_("Insufficient permissions."))
 
-    # Only root documents are indexed, a version stands for its root
-    return more_like_doc.root_document_id or more_like_doc.pk
+    return more_like_doc_id
 
 
 class SearchParams(NamedTuple):
@@ -1552,10 +1550,7 @@ class DocumentViewSet(
     )
     def suggestions(self, request, pk=None):
         doc = get_object_or_404(
-            Document.objects.select_related(
-                "owner",
-                "root_document__owner",
-            ).prefetch_related("versions"),
+            Document.objects.select_related("owner").prefetch_related("versions"),
             pk=pk,
         )
         if request.user is not None and not has_perms_owner_aware(
@@ -1615,10 +1610,7 @@ class DocumentViewSet(
     @method_decorator(cache_control(no_cache=True))
     def ai_suggestions(self, request, pk=None):
         doc = get_object_or_404(
-            Document.objects.select_related(
-                "owner",
-                "root_document__owner",
-            ).prefetch_related("versions"),
+            Document.objects.select_related("owner").prefetch_related("versions"),
             pk=pk,
         )
         if request.user is not None and not has_perms_owner_aware(
@@ -1864,14 +1856,9 @@ class DocumentViewSet(
         currentUser = request.user
         try:
             doc = (
-                Document.objects.select_related("owner", "root_document__owner")
+                Document.objects.select_related("owner")
                 .prefetch_related("notes")
-                .only(
-                    "pk",
-                    "owner__id",
-                    "root_document__id",
-                    "root_document__owner__id",
-                )
+                .only("pk", "owner__id")
                 .get(pk=pk)
             )
             if currentUser is not None and not has_perms_owner_aware(
@@ -1986,9 +1973,7 @@ class DocumentViewSet(
     def share_links(self, request, pk=None):
         currentUser = request.user
         try:
-            doc = Document.objects.select_related("owner", "root_document__owner").get(
-                pk=pk,
-            )
+            doc = Document.objects.select_related("owner").get(pk=pk)
             if currentUser is not None and not has_perms_owner_aware(
                 currentUser,
                 "change_document",
@@ -2023,11 +2008,10 @@ class DocumentViewSet(
         if not settings.AUDIT_LOG_ENABLED:
             return HttpResponseBadRequest("Audit log is disabled")
         try:
-            doc = Document.objects.select_related("root_document__owner").get(pk=pk)
-            root_doc = get_root_document(doc)
+            doc = Document.objects.get(pk=pk)
             if not request.user.has_perm("auditlog.view_logentry") or (
-                root_doc.owner is not None
-                and root_doc.owner != request.user
+                doc.owner is not None
+                and doc.owner != request.user
                 and not request.user.is_superuser
             ):
                 return HttpResponseForbidden(
@@ -2118,7 +2102,9 @@ class DocumentViewSet(
         documents = Document.objects.filter(pk__in=document_ids)
         if (
             request.user is not None
-            and documents.exclude(id__in=permitted_document_ids(request.user)).exists()
+            and documents.exclude(
+                pk__in=permitted_document_ids(request.user),
+            ).exists()
         ):
             return HttpResponseForbidden("Insufficient permissions")
 
@@ -2444,17 +2430,11 @@ class ChatStreamingView(GenericAPIView[Any]):
 
         if doc_id:
             try:
-                document = Document.objects.select_related(
-                    "root_document__owner",
-                ).get(id=doc_id)
+                document = Document.objects.get(id=doc_id)
             except Document.DoesNotExist:
                 return HttpResponseBadRequest("Document not found")
 
-            if not has_perms_owner_aware(
-                request.user,
-                "view_document",
-                document,
-            ):
+            if not has_perms_owner_aware(request.user, "view_document", document):
                 return HttpResponseForbidden("Insufficient permissions")
 
             documents = Document.objects.filter(pk=document.pk)
@@ -3010,8 +2990,12 @@ class DocumentOperationPermissionMixin(PassUserMixin, DocumentSelectionMixin):
             user.has_perm(
                 "documents.change_document",
             )
-            and not Document.global_objects.filter(pk__in=documents)
-            .exclude(pk__in=permitted_document_ids(user, perm="change_document"))
+            and not Document.global_objects.filter(
+                pk__in=[doc.pk for doc in root_docs],
+            )
+            .exclude(
+                pk__in=permitted_document_ids(user, perm="change_document"),
+            )
             .exists()
         )
 
@@ -3621,11 +3605,10 @@ class SelectionDataView(DocumentSelectionMixin, GenericAPIView[Any]):
             user=request.user,
             validated_data=serializer.validated_data,
         )
-        documents = Document.objects.filter(pk__in=ids)
-        if (
-            documents.count() != len(ids)
-            or documents.exclude(id__in=permitted_document_ids(request.user)).exists()
-        ):
+        permitted_documents = Document.objects.filter(
+            id__in=permitted_document_ids(request.user),
+        )
+        if permitted_documents.filter(pk__in=ids).count() != len(ids):
             return HttpResponseForbidden("Insufficient permissions")
 
         correspondents = Correspondent.objects.annotate(
@@ -4121,16 +4104,21 @@ class BulkDownloadView(DocumentSelectionMixin, GenericAPIView[Any]):
             validated_data=serializer.validated_data,
         )
         documents = Document.objects.filter(pk__in=ids)
+        versioned_documents = []
         compression = serializer.validated_data.get("compression")
         content = serializer.validated_data.get("content")
         follow_filename_format = serializer.validated_data.get("follow_formatting")
 
-        if documents.exclude(id__in=permitted_document_ids(request.user)).exists():
-            return HttpResponseForbidden("Insufficient permissions")
-        versioned_documents = [
-            get_latest_version_for_root(get_root_document(document))
-            for document in documents
-        ]
+        permitted_ids = set(permitted_document_ids(request.user))
+        for document in documents:
+            root_doc = get_root_document(document)
+            if root_doc.pk not in permitted_ids:
+                return HttpResponseForbidden("Insufficient permissions")
+            versioned_documents.append(
+                get_latest_version_for_root(
+                    root_doc,
+                ),
+            )
 
         if content == "both":
             strategy_class = OriginalAndArchiveStrategy
@@ -4802,23 +4790,19 @@ class ShareLinkBundleViewSet(PassUserMixin, ModelViewSet[ShareLinkBundle]):
                 },
             )
 
-        denied_id = (
-            documents_qs.exclude(id__in=permitted_document_ids(request.user))
-            .order_by("pk")
-            .values_list("pk", flat=True)
-            .first()
-        )
-        if denied_id is not None:
-            raise ValidationError(
-                {
-                    "document_ids": _(
-                        "Insufficient permissions to share document %(id)s.",
-                    )
-                    % {"id": denied_id},
-                },
-            )
-
         documents = list(documents_qs)
+        permitted_ids = set(permitted_document_ids(request.user))
+        for document in documents:
+            if document.pk not in permitted_ids:
+                raise ValidationError(
+                    {
+                        "document_ids": _(
+                            "Insufficient permissions to share document %(id)s.",
+                        )
+                        % {"id": document.pk},
+                    },
+                )
+
         document_map = {document.pk: document for document in documents}
         ordered_documents = [document_map[doc_id] for doc_id in document_ids]
 
@@ -5602,7 +5586,6 @@ class TrashView(ListModelMixin, PassUserMixin):
 
     class _TrashPermittedObjectsFilter(PermittedObjectsFilter):
         include_granted = False
-        parent_field = "root_document"
 
     filter_backends = (_TrashPermittedObjectsFilter,)
     pagination_class = StandardPagination
@@ -5634,7 +5617,7 @@ class TrashView(ListModelMixin, PassUserMixin):
             else self.filter_queryset(self.get_queryset()).all()
         )
         if docs.exclude(
-            id__in=permitted_document_ids(
+            pk__in=permitted_document_ids(
                 request.user,
                 perm="delete_document",
                 include_deleted=True,

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-10-08 18:39+0000\n"
+"POT-Creation-Date: 2026-10-06 15:12+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1652,49 +1652,49 @@ msgstr ""
 msgid "workflow runs"
 msgstr ""
 
-#: documents/serialisers.py:516 documents/serialisers.py:873
-#: documents/serialisers.py:2903 documents/views.py:344 documents/views.py:2751
+#: documents/serialisers.py:515 documents/serialisers.py:872
+#: documents/serialisers.py:2902 documents/views.py:343 documents/views.py:2732
 #: paperless_mail/serialisers.py:156
 msgid "Insufficient permissions."
 msgstr ""
 
-#: documents/serialisers.py:709
+#: documents/serialisers.py:708
 msgid "Invalid color."
 msgstr ""
 
-#: documents/serialisers.py:2370
+#: documents/serialisers.py:2369
 #, python-format
 msgid "File type %(type)s not supported"
 msgstr ""
 
-#: documents/serialisers.py:2414
+#: documents/serialisers.py:2413
 #, python-format
 msgid "Custom field id must be an integer: %(id)s"
 msgstr ""
 
-#: documents/serialisers.py:2421
+#: documents/serialisers.py:2420
 #, python-format
 msgid "Custom field with id %(id)s does not exist"
 msgstr ""
 
-#: documents/serialisers.py:2438 documents/serialisers.py:2448
+#: documents/serialisers.py:2437 documents/serialisers.py:2447
 msgid ""
 "Custom fields must be a list of integers or an object mapping ids to values."
 msgstr ""
 
-#: documents/serialisers.py:2443
+#: documents/serialisers.py:2442
 msgid "Some custom fields don't exist or were specified twice."
 msgstr ""
 
-#: documents/serialisers.py:2590
+#: documents/serialisers.py:2589
 msgid "Invalid variable detected."
 msgstr ""
 
-#: documents/serialisers.py:2959
+#: documents/serialisers.py:2958
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2989 documents/views.py:4807
+#: documents/serialisers.py:2988 documents/views.py:4787
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1945,40 +1945,40 @@ msgstr ""
 msgid ", "
 msgstr ""
 
-#: documents/views.py:337 documents/views.py:2748
+#: documents/views.py:336 documents/views.py:2729
 msgid "Invalid more_like_id"
 msgstr ""
 
-#: documents/views.py:1683
+#: documents/views.py:1676
 msgid "Invalid AI configuration."
 msgstr ""
 
-#: documents/views.py:1694
+#: documents/views.py:1687
 msgid "AI backend request timed out."
 msgstr ""
 
-#: documents/views.py:1706
+#: documents/views.py:1699
 msgid "AI backend rejected the request. Check logs for details."
 msgstr ""
 
-#: documents/views.py:2573 documents/views.py:2889
+#: documents/views.py:2554 documents/views.py:2870
 msgid "Specify only one of text, title_search, query, or more_like_id."
 msgstr ""
 
-#: documents/views.py:4823
+#: documents/views.py:4800
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:4870
+#: documents/views.py:4846
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:4934
+#: documents/views.py:4910
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:4948
+#: documents/views.py:4924
 msgid "The share link bundle is unavailable."
 msgstr ""
 

src/paperless_ai/ai_classifier.py

@@ -7,7 +7,6 @@ from documents.models import Document
 from documents.permissions import permitted_object_ids
 from documents.permissions import restrict_queryset_to_visible
 from documents.permissions import user_is_unrestricted
-from documents.versioning import annotate_effective_content
 from paperless.config import AIConfig
 from paperless_ai.base_model import ClassificationSuggestions
 from paperless_ai.base_model import TaxonomyChoiceDict
@@ -114,7 +113,7 @@ def build_prompt_without_rag(
 ) -> str:
     filename = document.filename or ""
     content = truncate_content(
-        (document.get_effective_content() or "")[:4000],
+        document.content[:4000] or "",
         chunk_size=config.llm_embedding_chunk_size,
         context_size=config.llm_context_size,
     )
@@ -228,9 +227,7 @@ def get_taxonomy_context(
 
         # similar_documents is already ordered by descending weight; don't lose it.
         similar_document_ids = [s["document_id"] for s in similar_documents]
-        similar_documents_by_id = annotate_effective_content(
-            Document.objects.all(),
-        ).in_bulk(similar_document_ids)
+        similar_documents_by_id = Document.objects.in_bulk(similar_document_ids)
         similar_docs = [
             similar_documents_by_id[document_id]
             for document_id in similar_document_ids
@@ -238,7 +235,7 @@ def get_taxonomy_context(
         ][:max_docs]
         context_blocks = []
         for similar in similar_docs:
-            text = (similar.get_effective_content() or "")[:1000]
+            text = similar.content[:1000] or ""
             title = similar.title or similar.filename or "Untitled"
             context_blocks.append(f"TITLE: {title}\n{text}")
     except Exception:

src/paperless_ai/embedding.py

@@ -135,6 +135,6 @@ def build_llm_index_text(doc: Document) -> str:
         lines.append(f"Custom Field - {instance.field.name}: {instance}")
 
     lines.append("\nContent:\n")
-    lines.append(doc.get_effective_content() or "")
+    lines.append(doc.content or "")
 
     return _normalize_llm_index_text("\n".join(lines))

src/paperless_ai/indexing.py

@@ -17,8 +17,6 @@ from documents.models import PaperlessTask
 from documents.utils import IterWrapper
 from documents.utils import QuerySetStream
 from documents.utils import identity
-from documents.versioning import annotate_effective_content
-from documents.versioning import root_document_ids
 from paperless.config import AIConfig
 from paperless_ai.db import db_connection_released
 from paperless_ai.embedding import build_llm_index_text
@@ -445,11 +443,11 @@ def update_llm_index(
                 "Skipping LLM index update: migration check deferred; "
                 "will retry next run."
             )
-    documents = annotate_effective_content(
-        Document.objects.filter(root_document__isnull=True)
-        .select_related("correspondent", "document_type", "storage_path")
-        .prefetch_related("tags", "notes", "custom_fields__field"),
-    )
+    documents = Document.objects.select_related(
+        "correspondent",
+        "document_type",
+        "storage_path",
+    ).prefetch_related("tags", "notes", "custom_fields__field")
     no_documents = not documents.exists()
 
     # Fast exit before touching config: nothing to index and no existing index.
@@ -485,7 +483,7 @@ def update_llm_index(
             msg = "LLM index rebuilt successfully."
         else:
             scoped_documents = (
-                documents.filter(id__in=root_document_ids(document_ids))
+                documents.filter(id__in=document_ids)
                 if document_ids is not None
                 else documents
             )
@@ -512,12 +510,7 @@ def update_llm_index(
 
 
 def llm_index_add_or_update_document(document: Document):
-    """
-    Add or atomically replace a document's chunks in the index. Only root
-    documents are indexed, so a version is indexed as its root document.
-    """
-    if document.root_document_id is not None:
-        document = document.root_document
+    """Add or atomically replace a document's chunks in the index."""
     config = AIConfig()
     new_nodes = build_document_node(
         document,
@@ -695,7 +688,7 @@ def retrieve_similar_nodes(
     )
 
     query_text = truncate_embedding_query(
-        (document.title or "") + "\n" + (document.get_effective_content() or ""),
+        (document.title or "") + "\n" + (document.content or ""),
         chunk_size=config.llm_embedding_chunk_size,
     )
     # Hold the shared read lock for the whole retrieval so the connection is

src/paperless_ai/tests/test_ai_classifier.py

@@ -55,7 +55,6 @@ def mock_document():
     doc.storage_path = None
     doc.archive_serial_number = "12345"
     doc.content = "This is the document content."
-    doc.get_effective_content.return_value = "This is the document content."
 
     cf1 = MagicMock(__str__=lambda x: "Value1")
     cf1.field = MagicMock()
@@ -435,55 +434,6 @@ def test_get_taxonomy_context_preserves_similarity_order_and_distinct_documents(
     )
 
 
-@pytest.mark.django_db
-class TestClassifierEffectiveContent:
-    """A root document's text for the LLM is its newest version's content."""
-
-    @staticmethod
-    def _root_with_version() -> Document:
-        root = DocumentFactory(title="Statement", content="stale text")
-        DocumentFactory(root_document=root, version_index=1, content="latest text")
-        return root
-
-    def test_prompt_uses_the_newest_versions_content(self) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The classification prompt is built for the root
-        THEN:
-            - It contains the newest version's content
-        """
-        prompt = build_prompt_without_rag(self._root_with_version(), AIConfig())
-
-        assert "latest text" in prompt
-        assert "stale text" not in prompt
-
-    @override_settings(LLM_EMBEDDING_BACKEND="huggingface")
-    def test_similar_document_context_uses_the_newest_versions_content(self) -> None:
-        """
-        GIVEN:
-            - A similar root document with a version
-        WHEN:
-            - The similar-document context is built
-        THEN:
-            - It contains the newest version's content
-        """
-        similar = self._root_with_version()
-        document = DocumentFactory(content="Some content")
-        fake_nodes = [
-            SimpleNamespace(metadata={"document_id": str(similar.pk)}, score=0.9),
-        ]
-
-        with patch(
-            "paperless_ai.ai_classifier.retrieve_similar_nodes",
-            return_value=fake_nodes,
-        ):
-            _candidates, context = get_taxonomy_context(document, user=None)
-
-        assert context == "TITLE: Statement\nlatest text"
-
-
 @pytest.mark.django_db
 @override_settings(LLM_EMBEDDING_BACKEND="huggingface")
 def test_get_taxonomy_context_no_similar_docs():

src/paperless_ai/tests/test_ai_indexing.py

@@ -388,108 +388,6 @@ def test_update_llm_index_partial_update(
     assert after[str(doc2.pk)] == before[str(doc2.pk)]
 
 
-@pytest.mark.django_db
-class TestLlmIndexVersions:
-    """The LLM index holds root documents only: a version is indexed as its root."""
-
-    def test_add_or_update_document_indexes_a_version_as_its_root(
-        self,
-        temp_llm_index_dir: Path,
-        mock_embed_model: FakeEmbedding,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The version is passed to llm_index_add_or_update_document
-        THEN:
-            - Only the root document is in the index
-        """
-        root = DocumentFactory(content="root content")
-        version = DocumentFactory(root_document=root, version_index=1)
-
-        indexing.llm_index_add_or_update_document(version)
-
-        with indexing.get_vector_store() as store:
-            indexed = store.get_modified_times()
-
-        assert set(indexed) == {str(root.pk)}
-
-    def test_rebuild_skips_versions(
-        self,
-        temp_llm_index_dir: Path,
-        mock_embed_model: FakeEmbedding,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The LLM index is rebuilt
-        THEN:
-            - Only the root document is in the index
-        """
-        root = DocumentFactory()
-        DocumentFactory(root_document=root, version_index=1)
-
-        indexing.update_llm_index(rebuild=True)
-
-        with indexing.get_vector_store() as store:
-            indexed = store.get_modified_times()
-
-        assert set(indexed) == {str(root.pk)}
-
-    def test_rebuild_indexes_the_newest_versions_content(
-        self,
-        temp_llm_index_dir: Path,
-        mock_embed_model: FakeEmbedding,
-        mocker: pytest_mock.MockerFixture,
-    ) -> None:
-        """
-        GIVEN:
-            - A root document with a version
-        WHEN:
-            - The LLM index is rebuilt
-        THEN:
-            - The root's text for the index is the version's content, answered
-              from the query rather than a query per document
-        """
-        root = DocumentFactory(content="stale text")
-        DocumentFactory(root_document=root, version_index=1, content="latest text")
-        spy = mocker.spy(indexing, "build_document_node")
-
-        indexing.update_llm_index(rebuild=True)
-
-        indexed = spy.call_args.args[0]
-        assert indexed.pk == root.pk
-        assert indexed.effective_content == "latest text"
-
-    def test_incremental_update_by_version_id_refreshes_the_root(
-        self,
-        temp_llm_index_dir: Path,
-        mock_embed_model: FakeEmbedding,
-    ) -> None:
-        """
-        GIVEN:
-            - An indexed root document with a version whose root was modified since
-        WHEN:
-            - An incremental update is scoped to the version's id
-        THEN:
-            - The root's entry is refreshed and no entry exists for the version
-        """
-        root = DocumentFactory()
-        version = DocumentFactory(root_document=root, version_index=1)
-        indexing.update_llm_index(rebuild=True)
-        Document.objects.filter(pk=root.pk).update(modified=timezone.now())
-        root.refresh_from_db()
-
-        indexing.update_llm_index(document_ids=[version.pk])
-
-        with indexing.get_vector_store() as store:
-            indexed = store.get_modified_times()
-
-        assert indexed == {str(root.pk): root.modified.isoformat()}
-
-
 @pytest.mark.django_db
 def test_add_or_update_document_updates_existing_entry(
     temp_llm_index_dir: Path,
@@ -739,7 +637,6 @@ class TestLlmIndexAddOrUpdateDocumentEmptyContent:
 
         doc = MagicMock(spec=Document)
         doc.id = 42
-        doc.root_document_id = None
         # Must not raise
         indexing.llm_index_add_or_update_document(doc)
 

src/paperless_ai/tests/test_embedding.py

@@ -12,7 +12,6 @@ from paperless_ai.embedding import _normalize_llm_index_text
 from paperless_ai.embedding import build_llm_index_text
 from paperless_ai.embedding import get_configured_model_name
 from paperless_ai.embedding import get_embedding_model
-from paperless_testing.factories import DocumentFactory
 
 
 @pytest.fixture
@@ -47,7 +46,6 @@ def mock_document():
     doc.correspondent.name = "Test Correspondent"
     doc.archive_serial_number = "12345"
     doc.content = "This is the document content."
-    doc.get_effective_content.return_value = "This is the document content."
 
     cf1 = MagicMock(__str__=lambda x: "Value1")
     cf1.field = MagicMock()
@@ -282,7 +280,7 @@ def test_build_llm_index_text(mock_document):
 
 
 def test_build_llm_index_text_normalizes_ocr_punctuation_runs(mock_document):
-    mock_document.get_effective_content.return_value = (
+    mock_document.content = (
         "Introduction ................................................ 7\n"
         "Hardware Limitation ________________________________________ 9\n"
         "Keep short punctuation like INV-100 and ellipses..."
@@ -296,43 +294,6 @@ def test_build_llm_index_text_normalizes_ocr_punctuation_runs(mock_document):
     assert "ellipses..." in result
 
 
-@pytest.mark.django_db
-class TestBuildLlmIndexTextVersions:
-    """A root document is indexed with its effective content, like in the search index."""
-
-    def test_root_uses_the_newest_versions_content(self) -> None:
-        """
-        GIVEN:
-            - A root document with two versions
-        WHEN:
-            - The LLM index text is built for the root
-        THEN:
-            - It contains the newest version's content and not the others'
-        """
-        root = DocumentFactory(content="stale text")
-        DocumentFactory(root_document=root, version_index=1, content="older text")
-        DocumentFactory(root_document=root, version_index=2, content="latest text")
-
-        text = build_llm_index_text(root)
-
-        assert "latest text" in text
-        assert "stale text" not in text
-        assert "older text" not in text
-
-    def test_root_without_versions_uses_its_own_content(self) -> None:
-        """
-        GIVEN:
-            - A root document without versions
-        WHEN:
-            - The LLM index text is built for it
-        THEN:
-            - It contains the document's own content
-        """
-        root = DocumentFactory(content="own text")
-
-        assert "own text" in build_llm_index_text(root)
-
-
 def test_normalize_llm_index_text_collapses_ocr_leaders_without_joining_lines():
     assert _normalize_llm_index_text("A........B\nC____D----E") == "A B\nC D E"