Merge branch 'dev' into feature-document-versions-1218

src/documents/__init__.py

@@ -1,5 +1,4 @@
 # this is here so that django finds the checks.
-from documents.checks import changed_password_check
 from documents.checks import parser_check
 
-__all__ = ["changed_password_check", "parser_check"]
+__all__ = ["parser_check"]

src/documents/admin.py

@@ -13,6 +13,7 @@ from documents.models import PaperlessTask
 from documents.models import SavedView
 from documents.models import SavedViewFilterRule
 from documents.models import ShareLink
+from documents.models import ShareLinkBundle
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.tasks import update_document_parent_tags
@@ -60,7 +61,6 @@ class DocumentAdmin(GuardedModelAdmin):
         "added",
         "modified",
         "mime_type",
-        "storage_type",
         "filename",
         "checksum",
         "archive_filename",
@@ -185,6 +185,22 @@ class ShareLinksAdmin(GuardedModelAdmin):
         return super().get_queryset(request).select_related("document__correspondent")
 
 
+class ShareLinkBundleAdmin(GuardedModelAdmin):
+    list_display = ("created", "status", "expiration", "owner", "slug")
+    list_filter = ("status", "created", "expiration", "owner")
+    search_fields = ("slug",)
+
+    def get_queryset(self, request):  # pragma: no cover
+        return (
+            super()
+            .get_queryset(request)
+            .select_related("owner")
+            .prefetch_related(
+                "documents",
+            )
+        )
+
+
 class CustomFieldsAdmin(GuardedModelAdmin):
     fields = ("name", "created", "data_type")
     readonly_fields = ("created", "data_type")
@@ -216,6 +232,7 @@ admin.site.register(StoragePath, StoragePathAdmin)
 admin.site.register(PaperlessTask, TaskAdmin)
 admin.site.register(Note, NotesAdmin)
 admin.site.register(ShareLink, ShareLinksAdmin)
+admin.site.register(ShareLinkBundle, ShareLinkBundleAdmin)
 admin.site.register(CustomField, CustomFieldsAdmin)
 admin.site.register(CustomFieldInstance, CustomFieldInstancesAdmin)
 

src/documents/apps.py

@@ -7,10 +7,11 @@ class DocumentsConfig(AppConfig):
 
     verbose_name = _("Documents")
 
-    def ready(self):
+    def ready(self) -> None:
         from documents.signals import document_consumption_finished
         from documents.signals import document_updated
         from documents.signals.handlers import add_inbox_tags
+        from documents.signals.handlers import add_or_update_document_in_llm_index
         from documents.signals.handlers import add_to_index
         from documents.signals.handlers import run_workflows_added
         from documents.signals.handlers import run_workflows_updated
@@ -26,6 +27,7 @@ class DocumentsConfig(AppConfig):
         document_consumption_finished.connect(set_storage_path)
         document_consumption_finished.connect(add_to_index)
         document_consumption_finished.connect(run_workflows_added)
+        document_consumption_finished.connect(add_or_update_document_in_llm_index)
         document_updated.connect(run_workflows_updated)
 
         import documents.schema  # noqa: F401

src/documents/barcodes.py

@@ -16,6 +16,7 @@ from pikepdf import Pdf
 from documents.converters import convert_from_tiff_to_pdf
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
+from documents.models import Document
 from documents.models import Tag
 from documents.plugins.base import ConsumeTaskPlugin
 from documents.plugins.base import StopConsumeTaskError
@@ -60,6 +61,20 @@ class Barcode:
         """
         return self.value.startswith(self.settings.barcode_asn_prefix)
 
+    @property
+    def is_tag(self) -> bool:
+        """
+        Returns True if the barcode value matches any configured tag mapping pattern,
+        False otherwise.
+
+        Note: This does NOT exclude ASN or separator barcodes - they can also be used
+        as tags if they match a tag mapping pattern (e.g., {"ASN12.*": "JOHN"}).
+        """
+        for regex in self.settings.barcode_tag_mapping:
+            if re.match(regex, self.value, flags=re.IGNORECASE):
+                return True
+        return False
+
 
 class BarcodePlugin(ConsumeTaskPlugin):
     NAME: str = "BarcodePlugin"
@@ -115,6 +130,24 @@ class BarcodePlugin(ConsumeTaskPlugin):
         self._tiff_conversion_done = False
         self.barcodes: list[Barcode] = []
 
+    def _apply_detected_asn(self, detected_asn: int) -> None:
+        """
+        Apply a detected ASN to metadata if allowed.
+        """
+        if (
+            self.metadata.skip_asn_if_exists
+            and Document.global_objects.filter(
+                archive_serial_number=detected_asn,
+            ).exists()
+        ):
+            logger.info(
+                f"Found ASN in barcode {detected_asn} but skipping because it already exists.",
+            )
+            return
+
+        logger.info(f"Found ASN in barcode: {detected_asn}")
+        self.metadata.asn = detected_asn
+
     def run(self) -> None:
         # Some operations may use PIL, override pixel setting if needed
         maybe_override_pixel_limit()
@@ -126,8 +159,14 @@ class BarcodePlugin(ConsumeTaskPlugin):
         self.detect()
 
         # try reading tags from barcodes
+        # If tag splitting is enabled, skip this on the original document - let each split document extract its own tags
+        # However, if we're processing a split document (original_path is set), extract tags
         if (
             self.settings.barcode_enable_tag
+            and (
+                not self.settings.barcode_tag_split
+                or self.input_doc.original_path is not None
+            )
             and (tags := self.tags) is not None
             and len(tags) > 0
         ):
@@ -164,6 +203,9 @@ class BarcodePlugin(ConsumeTaskPlugin):
                         mailrule_id=self.input_doc.mailrule_id,
                         # Can't use same folder or the consume might grab it again
                         original_file=(tmp_dir / new_document.name).resolve(),
+                        # Adding optional original_path for later uses in
+                        # workflow matching
+                        original_path=self.input_doc.original_file,
                     ),
                     # All the same metadata
                     self.metadata,
@@ -184,8 +226,7 @@ class BarcodePlugin(ConsumeTaskPlugin):
         # Update/overwrite an ASN if possible
         # After splitting, as otherwise each split document gets the same ASN
         if self.settings.barcode_enable_asn and (located_asn := self.asn) is not None:
-            logger.info(f"Found ASN in barcode: {located_asn}")
-            self.metadata.asn = located_asn
+            self._apply_detected_asn(located_asn)
 
     def cleanup(self) -> None:
         self.temp_dir.cleanup()
@@ -425,15 +466,24 @@ class BarcodePlugin(ConsumeTaskPlugin):
             for bc in self.barcodes
             if bc.is_separator and (not retain or (retain and bc.page > 0))
         }  # as below, dont include the first page if retain is enabled
-        if not self.settings.barcode_enable_asn:
-            return separator_pages
 
         # add the page numbers of the ASN barcodes
         # (except for first page, that might lead to infinite loops).
-        return {
-            **separator_pages,
-            **{bc.page: True for bc in self.barcodes if bc.is_asn and bc.page != 0},
-        }
+        if self.settings.barcode_enable_asn:
+            separator_pages = {
+                **separator_pages,
+                **{bc.page: True for bc in self.barcodes if bc.is_asn and bc.page != 0},
+            }
+
+        # add the page numbers of the TAG barcodes if splitting is enabled
+        # (except for first page, that might lead to infinite loops).
+        if self.settings.barcode_tag_split and self.settings.barcode_enable_tag:
+            separator_pages = {
+                **separator_pages,
+                **{bc.page: True for bc in self.barcodes if bc.is_tag and bc.page != 0},
+            }
+
+        return separator_pages
 
     def separate_pages(self, pages_to_split_on: dict[int, bool]) -> list[Path]:
         """

src/documents/bulk_edit.py

@@ -1,12 +1,12 @@
 from __future__ import annotations
 
+import hashlib
 import logging
 import tempfile
 from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Literal
 
-from celery import chain
 from celery import chord
 from celery import group
 from celery import shared_task
@@ -37,6 +37,42 @@ if TYPE_CHECKING:
 logger: logging.Logger = logging.getLogger("paperless.bulk_edit")
 
 
+@shared_task(bind=True)
+def restore_archive_serial_numbers_task(
+    self,
+    backup: dict[int, int | None],
+    *args,
+    **kwargs,
+) -> None:
+    restore_archive_serial_numbers(backup)
+
+
+def release_archive_serial_numbers(doc_ids: list[int]) -> dict[int, int | None]:
+    """
+    Clears ASNs on documents that are about to be replaced so new documents
+    can be assigned ASNs without uniqueness collisions. Returns a backup map
+    of doc_id -> previous ASN for potential restoration.
+    """
+    qs = Document.objects.filter(
+        id__in=doc_ids,
+        archive_serial_number__isnull=False,
+    ).only("pk", "archive_serial_number")
+    backup = dict(qs.values_list("pk", "archive_serial_number"))
+    qs.update(archive_serial_number=None)
+    logger.info(f"Released archive serial numbers for documents {list(backup.keys())}")
+    return backup
+
+
+def restore_archive_serial_numbers(backup: dict[int, int | None]) -> None:
+    """
+    Restores ASNs using the provided backup map, intended for
+    rollback when replacement consumption fails.
+    """
+    for doc_id, asn in backup.items():
+        Document.objects.filter(pk=doc_id).update(archive_serial_number=asn)
+    logger.info(f"Restored archive serial numbers for documents {list(backup.keys())}")
+
+
 def set_correspondent(
     doc_ids: list[int],
     correspondent: Correspondent,
@@ -304,10 +340,10 @@ def reprocess(doc_ids: list[int]) -> Literal["OK"]:
 
 def set_permissions(
     doc_ids: list[int],
-    set_permissions,
+    set_permissions: dict,
     *,
-    owner=None,
-    merge=False,
+    owner: User | None = None,
+    merge: bool = False,
 ) -> Literal["OK"]:
     qs = Document.objects.filter(id__in=doc_ids).select_related("owner")
 
@@ -389,6 +425,7 @@ def merge(
 
     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 = qs.get(id=doc_id)
@@ -404,6 +441,8 @@ def merge(
                 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}",
@@ -429,6 +468,8 @@ def merge(
                 DocumentMetadataOverrides.from_document(metadata_document)
             )
             overrides.title = metadata_document.title + " (merged)"
+            if metadata_document.archive_serial_number is not None:
+                handoff_asn = metadata_document.archive_serial_number
         else:
             overrides = DocumentMetadataOverrides()
     else:
@@ -436,6 +477,11 @@ def merge(
 
     if user is not None:
         overrides.owner_id = user.id
+    if not delete_originals:
+        overrides.skip_asn_if_exists = True
+
+    if delete_originals and handoff_asn is not None:
+        overrides.asn = handoff_asn
 
     logger.info("Adding merged document to the task queue.")
 
@@ -448,12 +494,20 @@ def merge(
     )
 
     if delete_originals:
+        backup = release_archive_serial_numbers(affected_docs)
         logger.info(
             "Queueing removal of original documents after consumption of merged document",
         )
-        chain(consume_task, delete.si(affected_docs)).delay()
-    else:
-        consume_task.delay()
+        try:
+            consume_task.apply_async(
+                link=[delete.si(affected_docs)],
+                link_error=[restore_archive_serial_numbers_task.s(backup)],
+            )
+        except Exception:
+            restore_archive_serial_numbers(backup)
+            raise
+        else:
+            consume_task.delay()
 
     return "OK"
 
@@ -495,6 +549,8 @@ def split(
                 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.",
                 )
@@ -509,10 +565,20 @@ def split(
                 )
 
             if delete_originals:
+                backup = release_archive_serial_numbers([doc.id])
                 logger.info(
                     "Queueing removal of original document after consumption of the split documents",
                 )
-                chord(header=consume_tasks, body=delete.si([doc.id])).delay()
+                try:
+                    chord(
+                        header=consume_tasks,
+                        body=delete.si([doc.id]),
+                    ).apply_async(
+                        link_error=[restore_archive_serial_numbers_task.s(backup)],
+                    )
+                except Exception:
+                    restore_archive_serial_numbers(backup)
+                    raise
             else:
                 group(consume_tasks).delay()
 
@@ -564,7 +630,7 @@ def delete_pages(doc_ids: list[int], pages: list[int]) -> Literal["OK"]:
 
 def edit_pdf(
     doc_ids: list[int],
-    operations: list[dict],
+    operations: list[dict[str, int]],
     *,
     delete_original: bool = False,
     update_document: bool = False,
@@ -639,7 +705,10 @@ def edit_pdf(
             )
             if user is not None:
                 overrides.owner_id = user.id
-
+            if not delete_original:
+                overrides.skip_asn_if_exists = True
+            if delete_original and len(pdf_docs) == 1:
+                overrides.asn = doc.archive_serial_number
             for idx, pdf in enumerate(pdf_docs, start=1):
                 filepath: Path = (
                     Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
@@ -658,7 +727,17 @@ def edit_pdf(
                 )
 
             if delete_original:
-                chord(header=consume_tasks, body=delete.si([doc.id])).delay()
+                backup = release_archive_serial_numbers([doc.id])
+                try:
+                    chord(
+                        header=consume_tasks,
+                        body=delete.si([doc.id]),
+                    ).apply_async(
+                        link_error=[restore_archive_serial_numbers_task.s(backup)],
+                    )
+                except Exception:
+                    restore_archive_serial_numbers(backup)
+                    raise
             else:
                 group(consume_tasks).delay()
 
@@ -671,11 +750,82 @@ def edit_pdf(
     return "OK"
 
 
+def remove_password(
+    doc_ids: list[int],
+    password: str,
+    *,
+    update_document: bool = False,
+    delete_original: bool = False,
+    include_metadata: bool = True,
+    user: User | None = None,
+) -> Literal["OK"]:
+    """
+    Remove password protection from PDF documents.
+    """
+    import pikepdf
+
+    for doc_id in doc_ids:
+        doc = Document.objects.get(id=doc_id)
+        try:
+            logger.info(
+                f"Attempting password removal from document {doc_ids[0]}",
+            )
+            with pikepdf.open(doc.source_path, password=password) as pdf:
+                temp_path = doc.source_path.with_suffix(".tmp.pdf")
+                pdf.remove_unreferenced_resources()
+                pdf.save(temp_path)
+
+                if update_document:
+                    # replace the original document with the unprotected one
+                    temp_path.replace(doc.source_path)
+                    doc.checksum = hashlib.md5(doc.source_path.read_bytes()).hexdigest()
+                    doc.page_count = len(pdf.pages)
+                    doc.save()
+                    update_document_content_maybe_archive_file.delay(document_id=doc.id)
+                else:
+                    consume_tasks = []
+                    overrides = (
+                        DocumentMetadataOverrides().from_document(doc)
+                        if include_metadata
+                        else DocumentMetadataOverrides()
+                    )
+                    if user is not None:
+                        overrides.owner_id = user.id
+
+                    filepath: Path = (
+                        Path(tempfile.mkdtemp(dir=settings.SCRATCH_DIR))
+                        / f"{doc.id}_unprotected.pdf"
+                    )
+                    temp_path.replace(filepath)
+                    consume_tasks.append(
+                        consume_file.s(
+                            ConsumableDocument(
+                                source=DocumentSource.ConsumeFolder,
+                                original_file=filepath,
+                            ),
+                            overrides,
+                        ),
+                    )
+
+                    if delete_original:
+                        chord(header=consume_tasks, body=delete.si([doc.id])).delay()
+                    else:
+                        group(consume_tasks).delay()
+
+        except Exception as e:
+            logger.exception(f"Error removing password from document {doc.id}: {e}")
+            raise ValueError(
+                f"An error occurred while removing the password: {e}",
+            ) from e
+
+    return "OK"
+
+
 def reflect_doclinks(
     document: Document,
     field: CustomField,
     target_doc_ids: list[int],
-):
+) -> None:
     """
     Add or remove 'symmetrical' links to `document` on all `target_doc_ids`
     """
@@ -738,7 +888,7 @@ def remove_doclink(
     document: Document,
     field: CustomField,
     target_doc_id: int,
-):
+) -> None:
     """
     Removes a 'symmetrical' link to `document` from the target document's existing custom field instance
     """

src/documents/caching.py

@@ -41,6 +41,7 @@ class SuggestionCacheData:
 CLASSIFIER_VERSION_KEY: Final[str] = "classifier_version"
 CLASSIFIER_HASH_KEY: Final[str] = "classifier_hash"
 CLASSIFIER_MODIFIED_KEY: Final[str] = "classifier_modified"
+LLM_CACHE_CLASSIFIER_VERSION: Final[int] = 1000  # Marker distinguishing LLM suggestions
 
 CACHE_1_MINUTE: Final[int] = 60
 CACHE_5_MINUTES: Final[int] = 5 * CACHE_1_MINUTE
@@ -196,6 +197,54 @@ def refresh_suggestions_cache(
     cache.touch(doc_key, timeout)
 
 
+def get_llm_suggestion_cache(
+    document_id: int,
+    backend: str,
+) -> SuggestionCacheData | None:
+    doc_key = get_suggestion_cache_key(document_id)
+    data: SuggestionCacheData = cache.get(doc_key)
+
+    if data and data.classifier_hash == backend:
+        return data
+
+    return None
+
+
+def set_llm_suggestions_cache(
+    document_id: int,
+    suggestions: dict,
+    *,
+    backend: str,
+    timeout: int = CACHE_50_MINUTES,
+) -> None:
+    """
+    Cache LLM-generated suggestions using a backend-specific identifier (e.g. 'openai:gpt-4').
+    """
+    doc_key = get_suggestion_cache_key(document_id)
+    cache.set(
+        doc_key,
+        SuggestionCacheData(
+            classifier_version=LLM_CACHE_CLASSIFIER_VERSION,
+            classifier_hash=backend,
+            suggestions=suggestions,
+        ),
+        timeout,
+    )
+
+
+def invalidate_llm_suggestions_cache(
+    document_id: int,
+) -> None:
+    """
+    Invalidate the LLM suggestions cache for a specific document and backend.
+    """
+    doc_key = get_suggestion_cache_key(document_id)
+    data: SuggestionCacheData = cache.get(doc_key)
+
+    if data:
+        cache.delete(doc_key)
+
+
 def get_metadata_cache_key(document_id: int) -> str:
     """
     Returns the basic key for a document's metadata

src/documents/checks.py

@@ -1,60 +1,12 @@
-import textwrap
-
 from django.conf import settings
 from django.core.checks import Error
 from django.core.checks import Warning
 from django.core.checks import register
-from django.core.exceptions import FieldError
-from django.db.utils import OperationalError
-from django.db.utils import ProgrammingError
 
 from documents.signals import document_consumer_declaration
 from documents.templating.utils import convert_format_str_to_template_format
 
 
-@register()
-def changed_password_check(app_configs, **kwargs):
-    from documents.models import Document
-    from paperless.db import GnuPG
-
-    try:
-        encrypted_doc = (
-            Document.objects.filter(
-                storage_type=Document.STORAGE_TYPE_GPG,
-            )
-            .only("pk", "storage_type")
-            .first()
-        )
-    except (OperationalError, ProgrammingError, FieldError):
-        return []  # No documents table yet
-
-    if encrypted_doc:
-        if not settings.PASSPHRASE:
-            return [
-                Error(
-                    "The database contains encrypted documents but no password is set.",
-                ),
-            ]
-
-        if not GnuPG.decrypted(encrypted_doc.source_file):
-            return [
-                Error(
-                    textwrap.dedent(
-                        """
-                The current password doesn't match the password of the
-                existing documents.
-
-                If you intend to change your password, you must first export
-                all of the old documents, start fresh with the new password
-                and then re-import them."
-                """,
-                    ),
-                ),
-            ]
-
-    return []
-
-
 @register()
 def parser_check(app_configs, **kwargs):
     parsers = []

src/documents/classifier.py

@@ -122,7 +122,7 @@ class DocumentClassifier:
             )
         self._stop_words = None
 
-    def _update_data_vectorizer_hash(self):
+    def _update_data_vectorizer_hash(self) -> None:
         self.data_vectorizer_hash = sha256(
             pickle.dumps(self.data_vectorizer),
         ).hexdigest()

src/documents/consumer.py

@@ -5,6 +5,7 @@ import tempfile
 from enum import Enum
 from pathlib import Path
 from typing import TYPE_CHECKING
+from typing import Final
 
 import magic
 from django.conf import settings
@@ -32,12 +33,12 @@ from documents.models import WorkflowTrigger
 from documents.parsers import DocumentParser
 from documents.parsers import ParseError
 from documents.parsers import get_parser_class_for_mime_type
-from documents.parsers import parse_date
 from documents.permissions import set_permissions_for_object
 from documents.plugins.base import AlwaysRunPluginMixin
 from documents.plugins.base import ConsumeTaskPlugin
 from documents.plugins.base import NoCleanupPluginMixin
 from documents.plugins.base import NoSetupPluginMixin
+from documents.plugins.date_parsing import get_date_parser
 from documents.plugins.helpers import ProgressManager
 from documents.plugins.helpers import ProgressStatusOptions
 from documents.signals import document_consumption_finished
@@ -49,6 +50,8 @@ from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
 from paperless_mail.parsers import MailDocumentParser
 
+LOGGING_NAME: Final[str] = "paperless.consumer"
+
 
 class WorkflowTriggerPlugin(
     NoCleanupPluginMixin,
@@ -126,7 +129,7 @@ class ConsumerPluginMixin:
         status: ProgressStatusOptions,
         message: ConsumerStatusShortMessage | str | None = None,
         document_id=None,
-    ):  # pragma: no cover
+    ) -> None:  # pragma: no cover
         self.status_mgr.send_progress(
             status,
             message,
@@ -162,9 +165,9 @@ class ConsumerPlugin(
     ConsumerPluginMixin,
     ConsumeTaskPlugin,
 ):
-    logging_name = "paperless.consumer"
+    logging_name = LOGGING_NAME
 
-    def run_pre_consume_script(self):
+    def run_pre_consume_script(self) -> None:
         """
         If one is configured and exists, run the pre-consume script and
         handle its output and/or errors
@@ -207,7 +210,7 @@ class ConsumerPlugin(
                 exception=e,
             )
 
-    def run_post_consume_script(self, document: Document):
+    def run_post_consume_script(self, document: Document) -> None:
         """
         If one is configured and exists, run the pre-consume script and
         handle its output and/or errors
@@ -367,7 +370,10 @@ class ConsumerPlugin(
                 tempdir.cleanup()
             raise
 
-        def progress_callback(current_progress, max_progress):  # pragma: no cover
+        def progress_callback(
+            current_progress,
+            max_progress,
+        ) -> None:  # pragma: no cover
             # recalculate progress to be within 20 and 80
             p = int((current_progress / max_progress) * 50 + 20)
             self._send_progress(p, 100, ProgressStatusOptions.WORKING)
@@ -432,7 +438,8 @@ class ConsumerPlugin(
                     ProgressStatusOptions.WORKING,
                     ConsumerStatusShortMessage.PARSE_DATE,
                 )
-                date = parse_date(self.filename, text)
+                with get_date_parser() as date_parser:
+                    date = next(date_parser.parse(self.filename, text), None)
             archive_path = document_parser.get_archive_path()
             page_count = document_parser.get_page_count(self.working_copy, mime_type)
 
@@ -535,7 +542,6 @@ class ConsumerPlugin(
                     create_source_path_directory(document.source_path)
 
                     self._write(
-                        document.storage_type,
                         self.unmodified_original
                         if self.unmodified_original is not None
                         else self.working_copy,
@@ -543,7 +549,6 @@ class ConsumerPlugin(
                     )
 
                     self._write(
-                        document.storage_type,
                         thumbnail,
                         document.thumbnail_path,
                     )
@@ -555,7 +560,6 @@ class ConsumerPlugin(
                         )
                         create_source_path_directory(document.archive_path)
                         self._write(
-                            document.storage_type,
                             archive_path,
                             document.archive_path,
                         )
@@ -675,8 +679,6 @@ class ConsumerPlugin(
             )
             self.log.debug(f"Creation date from st_mtime: {create_date}")
 
-        storage_type = Document.STORAGE_TYPE_UNENCRYPTED
-
         if self.metadata.filename:
             title = Path(self.metadata.filename).stem
         else:
@@ -703,7 +705,6 @@ class ConsumerPlugin(
             checksum=hashlib.md5(file_for_checksum.read_bytes()).hexdigest(),
             created=create_date,
             modified=create_date,
-            storage_type=storage_type,
             page_count=page_count,
             original_filename=self.filename,
         )
@@ -714,7 +715,7 @@ class ConsumerPlugin(
 
         return document
 
-    def apply_overrides(self, document):
+    def apply_overrides(self, document) -> None:
         if self.metadata.correspondent_id:
             document.correspondent = Correspondent.objects.get(
                 pk=self.metadata.correspondent_id,
@@ -774,7 +775,7 @@ class ConsumerPlugin(
                 }
                 CustomFieldInstance.objects.create(**args)  # adds to document
 
-    def _write(self, storage_type, source, target):
+    def _write(self, source, target) -> None:
         with (
             Path(source).open("rb") as read_file,
             Path(target).open("wb") as write_file,
@@ -797,9 +798,9 @@ class ConsumerPreflightPlugin(
     ConsumeTaskPlugin,
 ):
     NAME: str = "ConsumerPreflightPlugin"
-    logging_name = "paperless.consumer"
+    logging_name = LOGGING_NAME
 
-    def pre_check_file_exists(self):
+    def pre_check_file_exists(self) -> None:
         """
         Confirm the input file still exists where it should
         """
@@ -813,7 +814,7 @@ class ConsumerPreflightPlugin(
                 f"Cannot consume {self.input_doc.original_file}: File not found.",
             )
 
-    def pre_check_duplicate(self):
+    def pre_check_duplicate(self) -> None:
         """
         Using the MD5 of the file, check this exact file doesn't already exist
         """
@@ -823,21 +824,47 @@ class ConsumerPreflightPlugin(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
         )
         if existing_doc.exists():
-            msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
-            log_msg = f"Not consuming {self.filename}: It is a duplicate of {existing_doc.get().title} (#{existing_doc.get().pk})."
-
-            if existing_doc.first().deleted_at is not None:
-                msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
-                log_msg += " Note: existing document is in the trash."
-
-            if settings.CONSUMER_DELETE_DUPLICATES:
-                Path(self.input_doc.original_file).unlink()
-            self._fail(
-                msg,
-                log_msg,
+            existing_doc = existing_doc.order_by("-created")
+            duplicates_in_trash = existing_doc.filter(deleted_at__isnull=False)
+            log_msg = (
+                f"Consuming duplicate {self.filename}: "
+                f"{existing_doc.count()} existing document(s) share the same content."
             )
 
-    def pre_check_directories(self):
+            if duplicates_in_trash.exists():
+                log_msg += " Note: at least one existing document is in the trash."
+
+            self.log.warning(log_msg)
+
+            if settings.CONSUMER_DELETE_DUPLICATES:
+                duplicate = existing_doc.first()
+                duplicate_label = (
+                    duplicate.title
+                    or duplicate.original_filename
+                    or (Path(duplicate.filename).name if duplicate.filename else None)
+                    or str(duplicate.pk)
+                )
+
+                Path(self.input_doc.original_file).unlink()
+
+                failure_msg = (
+                    f"Not consuming {self.filename}: "
+                    f"It is a duplicate of {duplicate_label} (#{duplicate.pk})"
+                )
+                status_msg = ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS
+
+                if duplicates_in_trash.exists():
+                    status_msg = (
+                        ConsumerStatusShortMessage.DOCUMENT_ALREADY_EXISTS_IN_TRASH
+                    )
+                    failure_msg += " Note: existing document is in the trash."
+
+                self._fail(
+                    status_msg,
+                    failure_msg,
+                )
+
+    def pre_check_directories(self) -> None:
         """
         Ensure all required directories exist before attempting to use them
         """
@@ -846,12 +873,38 @@ class ConsumerPreflightPlugin(
         settings.ORIGINALS_DIR.mkdir(parents=True, exist_ok=True)
         settings.ARCHIVE_DIR.mkdir(parents=True, exist_ok=True)
 
-    def pre_check_asn_value(self):
+    def run(self) -> None:
+        self._send_progress(
+            0,
+            100,
+            ProgressStatusOptions.STARTED,
+            ConsumerStatusShortMessage.NEW_FILE,
+        )
+
+        # Make sure that preconditions for consuming the file are met.
+
+        self.pre_check_file_exists()
+        self.pre_check_duplicate()
+        self.pre_check_directories()
+
+
+class AsnCheckPlugin(
+    NoCleanupPluginMixin,
+    NoSetupPluginMixin,
+    AlwaysRunPluginMixin,
+    LoggingMixin,
+    ConsumerPluginMixin,
+    ConsumeTaskPlugin,
+):
+    NAME: str = "AsnCheckPlugin"
+    logging_name = LOGGING_NAME
+
+    def pre_check_asn_value(self) -> None:
         """
         Check that if override_asn is given, it is unique and within a valid range
         """
         if self.metadata.asn is None:
-            # check not necessary in case no ASN gets set
+            # if ASN is None
             return
         # Validate the range is above zero and less than uint32_t max
         # otherwise, Whoosh can't handle it in the index
@@ -883,16 +936,4 @@ class ConsumerPreflightPlugin(
             )
 
     def run(self) -> None:
-        self._send_progress(
-            0,
-            100,
-            ProgressStatusOptions.STARTED,
-            ConsumerStatusShortMessage.NEW_FILE,
-        )
-
-        # Make sure that preconditions for consuming the file are met.
-
-        self.pre_check_file_exists()
-        self.pre_check_duplicate()
-        self.pre_check_directories()
         self.pre_check_asn_value()

src/documents/data_models.py

@@ -22,7 +22,7 @@ class DocumentMetadataOverrides:
     document_type_id: int | None = None
     tag_ids: list[int] | None = None
     storage_path_id: int | None = None
-    created: datetime.datetime | None = None
+    created: datetime.date | None = None
     asn: int | None = None
     owner_id: int | None = None
     view_users: list[int] | None = None
@@ -30,6 +30,7 @@ class DocumentMetadataOverrides:
     change_users: list[int] | None = None
     change_groups: list[int] | None = None
     custom_fields: dict | None = None
+    skip_asn_if_exists: bool = False
 
     def update(self, other: "DocumentMetadataOverrides") -> "DocumentMetadataOverrides":
         """
@@ -49,6 +50,8 @@ class DocumentMetadataOverrides:
             self.storage_path_id = other.storage_path_id
         if other.owner_id is not None:
             self.owner_id = other.owner_id
+        if other.skip_asn_if_exists:
+            self.skip_asn_if_exists = True
 
         # merge
         if self.tag_ids is None:
@@ -100,6 +103,7 @@ class DocumentMetadataOverrides:
         overrides.storage_path_id = doc.storage_path.id if doc.storage_path else None
         overrides.owner_id = doc.owner.id if doc.owner else None
         overrides.tag_ids = list(doc.tags.values_list("id", flat=True))
+        overrides.created = doc.created
 
         overrides.view_users = list(
             get_users_with_perms(
@@ -114,7 +118,7 @@ class DocumentMetadataOverrides:
             ).values_list("id", flat=True),
         )
         overrides.custom_fields = {
-            custom_field.id: custom_field.value
+            custom_field.field.id: custom_field.value
             for custom_field in doc.custom_fields.all()
         }
 
@@ -157,10 +161,11 @@ class ConsumableDocument:
     source: DocumentSource
     original_file: Path
     head_version_id: int | None = None
+    original_path: Path | None = None
     mailrule_id: int | None = None
     mime_type: str = dataclasses.field(init=False, default=None)
 
-    def __post_init__(self):
+    def __post_init__(self) -> None:
         """
         After a dataclass is initialized, this is called to finalize some data
         1. Make sure the original path is an absolute, fully qualified path

src/documents/file_handling.py

@@ -99,37 +99,37 @@ def generate_unique_filename(doc, *, archive_filename=False) -> Path:
             return new_filename
 
 
+def format_filename(document: Document, template_str: str) -> str | None:
+    rendered_filename = validate_filepath_template_and_render(
+        template_str,
+        document,
+    )
+    if rendered_filename is None:
+        return None
+
+    # Apply this setting.  It could become a filter in the future (or users could use |default)
+    if settings.FILENAME_FORMAT_REMOVE_NONE:
+        rendered_filename = rendered_filename.replace("/-none-/", "/")
+        rendered_filename = rendered_filename.replace(" -none-", "")
+        rendered_filename = rendered_filename.replace("-none-", "")
+        rendered_filename = rendered_filename.strip(os.sep)
+
+    rendered_filename = rendered_filename.replace(
+        "-none-",
+        "none",
+    )  # backward compatibility
+
+    return rendered_filename
+
+
 def generate_filename(
     doc: Document,
     *,
     counter=0,
-    append_gpg=True,
     archive_filename=False,
 ) -> Path:
     base_path: Path | None = None
 
-    def format_filename(document: Document, template_str: str) -> str | None:
-        rendered_filename = validate_filepath_template_and_render(
-            template_str,
-            document,
-        )
-        if rendered_filename is None:
-            return None
-
-        # Apply this setting.  It could become a filter in the future (or users could use |default)
-        if settings.FILENAME_FORMAT_REMOVE_NONE:
-            rendered_filename = rendered_filename.replace("/-none-/", "/")
-            rendered_filename = rendered_filename.replace(" -none-", "")
-            rendered_filename = rendered_filename.replace("-none-", "")
-            rendered_filename = rendered_filename.strip(os.sep)
-
-        rendered_filename = rendered_filename.replace(
-            "-none-",
-            "none",
-        )  # backward compatibility
-
-        return rendered_filename
-
     # Determine the source of the format string
     if doc.storage_path is not None:
         filename_format = doc.storage_path.path
@@ -169,8 +169,4 @@ def generate_filename(
         final_filename = f"{doc.pk:07}{counter_str}{filetype_str}"
         full_path = Path(final_filename)
 
-    # Add GPG extension if needed
-    if append_gpg and doc.storage_type == doc.STORAGE_TYPE_GPG:
-        full_path = full_path.with_suffix(full_path.suffix + ".gpg")
-
     return full_path

src/documents/filters.py

@@ -39,6 +39,7 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import PaperlessTask
 from documents.models import ShareLink
+from documents.models import ShareLinkBundle
 from documents.models import StoragePath
 from documents.models import Tag
 
@@ -92,6 +93,12 @@ class TagFilterSet(FilterSet):
             "name": CHAR_KWARGS,
         }
 
+    is_root = BooleanFilter(
+        label="Is root tag",
+        field_name="tn_parent",
+        lookup_expr="isnull",
+    )
+
 
 class DocumentTypeFilterSet(FilterSet):
     class Meta:
@@ -113,7 +120,7 @@ class StoragePathFilterSet(FilterSet):
 
 
 class ObjectFilter(Filter):
-    def __init__(self, *, exclude=False, in_list=False, field_name=""):
+    def __init__(self, *, exclude=False, in_list=False, field_name="") -> None:
         super().__init__()
         self.exclude = exclude
         self.in_list = in_list
@@ -154,6 +161,7 @@ class InboxFilter(Filter):
 @extend_schema_field(serializers.CharField)
 class TitleContentFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             return qs.filter(Q(title__icontains=value) | Q(content__icontains=value))
         else:
@@ -208,6 +216,7 @@ class CustomFieldFilterSet(FilterSet):
 @extend_schema_field(serializers.CharField)
 class CustomFieldsFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             fields_with_matching_selects = CustomField.objects.filter(
                 extra_data__icontains=value,
@@ -238,6 +247,7 @@ class CustomFieldsFilter(Filter):
 
 class MimeTypeFilter(Filter):
     def filter(self, qs, value):
+        value = value.strip() if isinstance(value, str) else value
         if value:
             return qs.filter(mime_type__icontains=value)
         else:
@@ -245,7 +255,7 @@ class MimeTypeFilter(Filter):
 
 
 class SelectField(serializers.CharField):
-    def __init__(self, custom_field: CustomField):
+    def __init__(self, custom_field: CustomField) -> None:
         self._options = custom_field.extra_data["select_options"]
         super().__init__(max_length=16)
 
@@ -666,7 +676,7 @@ class CustomFieldQueryParser:
 
 @extend_schema_field(serializers.CharField)
 class CustomFieldQueryFilter(Filter):
-    def __init__(self, validation_prefix):
+    def __init__(self, validation_prefix) -> None:
         """
         A filter that filters documents based on custom field name and value.
 
@@ -787,6 +797,29 @@ class ShareLinkFilterSet(FilterSet):
         }
 
 
+class ShareLinkBundleFilterSet(FilterSet):
+    documents = Filter(method="filter_documents")
+
+    class Meta:
+        model = ShareLinkBundle
+        fields = {
+            "created": DATETIME_KWARGS,
+            "expiration": DATETIME_KWARGS,
+            "status": ["exact"],
+        }
+
+    def filter_documents(self, queryset, name, value):
+        ids = []
+        if value:
+            try:
+                ids = [int(item) for item in value.split(",") if item]
+            except ValueError:
+                return queryset.none()
+        if not ids:
+            return queryset
+        return queryset.filter(documents__in=ids).distinct()
+
+
 class PaperlessTaskFilterSet(FilterSet):
     acknowledged = BooleanFilter(
         label="Acknowledged",

src/documents/index.py

@@ -10,9 +10,11 @@ from datetime import time
 from datetime import timedelta
 from datetime import timezone
 from shutil import rmtree
+from time import sleep
 from typing import TYPE_CHECKING
 from typing import Literal
 
+from dateutil.relativedelta import relativedelta
 from django.conf import settings
 from django.utils import timezone as django_timezone
 from django.utils.timezone import get_current_timezone
@@ -31,6 +33,7 @@ from whoosh.highlight import HtmlFormatter
 from whoosh.idsets import BitSet
 from whoosh.idsets import DocIdSet
 from whoosh.index import FileIndex
+from whoosh.index import LockError
 from whoosh.index import create_in
 from whoosh.index import exists_in
 from whoosh.index import open_dir
@@ -96,11 +99,33 @@ def get_schema() -> Schema:
 
 
 def open_index(*, recreate=False) -> FileIndex:
-    try:
-        if exists_in(settings.INDEX_DIR) and not recreate:
-            return open_dir(settings.INDEX_DIR, schema=get_schema())
-    except Exception:
-        logger.exception("Error while opening the index, recreating.")
+    transient_exceptions = (FileNotFoundError, LockError)
+    max_retries = 3
+    retry_delay = 0.1
+
+    for attempt in range(max_retries + 1):
+        try:
+            if exists_in(settings.INDEX_DIR) and not recreate:
+                return open_dir(settings.INDEX_DIR, schema=get_schema())
+            break
+        except transient_exceptions as exc:
+            is_last_attempt = attempt == max_retries or recreate
+            if is_last_attempt:
+                logger.exception(
+                    "Error while opening the index after retries, recreating.",
+                )
+                break
+
+            logger.warning(
+                "Transient error while opening the index (attempt %s/%s): %s. Retrying.",
+                attempt + 1,
+                max_retries + 1,
+                exc,
+            )
+            sleep(retry_delay)
+        except Exception:
+            logger.exception("Error while opening the index, recreating.")
+            break
 
     # create_in doesn't handle corrupted indexes very well, remove the directory entirely first
     if settings.INDEX_DIR.is_dir():
@@ -287,15 +312,75 @@ class DelayedQuery:
         self.first_score = None
         self.filter_queryset = filter_queryset
         self.suggested_correction = None
+        self._manual_hits_cache: list | None = None
 
     def __len__(self) -> int:
+        if self._manual_sort_requested():
+            manual_hits = self._manual_hits()
+            return len(manual_hits)
+
         page = self[0:1]
         return len(page)
 
+    def _manual_sort_requested(self):
+        ordering = self.query_params.get("ordering", "")
+        return ordering.lstrip("-").startswith("custom_field_")
+
+    def _manual_hits(self):
+        if self._manual_hits_cache is None:
+            q, mask, suggested_correction = self._get_query()
+            self.suggested_correction = suggested_correction
+
+            results = self.searcher.search(
+                q,
+                mask=mask,
+                filter=MappedDocIdSet(self.filter_queryset, self.searcher.ixreader),
+                limit=None,
+            )
+            results.fragmenter = highlight.ContextFragmenter(surround=50)
+            results.formatter = HtmlFormatter(tagname="span", between=" ... ")
+
+            if not self.first_score and len(results) > 0:
+                self.first_score = results[0].score
+
+            if self.first_score:
+                results.top_n = [
+                    (
+                        (hit[0] / self.first_score) if self.first_score else None,
+                        hit[1],
+                    )
+                    for hit in results.top_n
+                ]
+
+            hits_by_id = {hit["id"]: hit for hit in results}
+            matching_ids = list(hits_by_id.keys())
+
+            ordered_ids = list(
+                self.filter_queryset.filter(id__in=matching_ids).values_list(
+                    "id",
+                    flat=True,
+                ),
+            )
+            ordered_ids = list(dict.fromkeys(ordered_ids))
+
+            self._manual_hits_cache = [
+                hits_by_id[_id] for _id in ordered_ids if _id in hits_by_id
+            ]
+        return self._manual_hits_cache
+
     def __getitem__(self, item):
         if item.start in self.saved_results:
             return self.saved_results[item.start]
 
+        if self._manual_sort_requested():
+            manual_hits = self._manual_hits()
+            start = 0 if item.start is None else item.start
+            stop = item.stop
+            hits = manual_hits[start:stop] if stop is not None else manual_hits[start:]
+            page = ManualResultsPage(hits)
+            self.saved_results[start] = page
+            return page
+
         q, mask, suggested_correction = self._get_query()
         self.suggested_correction = suggested_correction
         sortedby, reverse = self._get_query_sortedby()
@@ -315,21 +400,33 @@ class DelayedQuery:
         if not self.first_score and len(page.results) > 0 and sortedby is None:
             self.first_score = page.results[0].score
 
-        page.results.top_n = list(
-            map(
-                lambda hit: (
-                    (hit[0] / self.first_score) if self.first_score else None,
-                    hit[1],
-                ),
-                page.results.top_n,
-            ),
-        )
+        page.results.top_n = [
+            (
+                (hit[0] / self.first_score) if self.first_score else None,
+                hit[1],
+            )
+            for hit in page.results.top_n
+        ]
 
         self.saved_results[item.start] = page
 
         return page
 
 
+class ManualResultsPage(list):
+    def __init__(self, hits) -> None:
+        super().__init__(hits)
+        self.results = ManualResults(hits)
+
+
+class ManualResults:
+    def __init__(self, hits) -> None:
+        self._docnums = [hit.docnum for hit in hits]
+
+    def docs(self):
+        return self._docnums
+
+
 class LocalDateParser(English):
     def reverse_timezone_offset(self, d):
         return (d.replace(tzinfo=django_timezone.get_current_timezone())).astimezone(
@@ -461,32 +558,84 @@ def get_permissions_criterias(user: User | None = None) -> list:
 def rewrite_natural_date_keywords(query_string: str) -> str:
     """
     Rewrites natural date keywords (e.g. added:today or added:"yesterday") to UTC range syntax for Whoosh.
+    This resolves timezone issues with date parsing in Whoosh as well as adding support for more
+    natural date keywords.
     """
 
     tz = get_current_timezone()
     local_now = now().astimezone(tz)
-
     today = local_now.date()
-    yesterday = today - timedelta(days=1)
 
-    ranges = {
-        "today": (
-            datetime.combine(today, time.min, tzinfo=tz),
-            datetime.combine(today, time.max, tzinfo=tz),
-        ),
-        "yesterday": (
-            datetime.combine(yesterday, time.min, tzinfo=tz),
-            datetime.combine(yesterday, time.max, tzinfo=tz),
-        ),
-    }
-
-    pattern = r"(\b(?:added|created))\s*:\s*[\"']?(today|yesterday)[\"']?"
+    # all supported Keywords
+    pattern = r"(\b(?:added|created|modified))\s*:\s*[\"']?(today|yesterday|this month|previous month|previous week|previous quarter|this year|previous year)[\"']?"
 
     def repl(m):
-        field, keyword = m.group(1), m.group(2)
-        start, end = ranges[keyword]
+        field = m.group(1)
+        keyword = m.group(2).lower()
+
+        match keyword:
+            case "today":
+                start = datetime.combine(today, time.min, tzinfo=tz)
+                end = datetime.combine(today, time.max, tzinfo=tz)
+
+            case "yesterday":
+                yesterday = today - timedelta(days=1)
+                start = datetime.combine(yesterday, time.min, tzinfo=tz)
+                end = datetime.combine(yesterday, time.max, tzinfo=tz)
+
+            case "this month":
+                start = datetime(local_now.year, local_now.month, 1, 0, 0, 0, tzinfo=tz)
+                end = start + relativedelta(months=1) - timedelta(seconds=1)
+
+            case "previous month":
+                this_month_start = datetime(
+                    local_now.year,
+                    local_now.month,
+                    1,
+                    0,
+                    0,
+                    0,
+                    tzinfo=tz,
+                )
+                start = this_month_start - relativedelta(months=1)
+                end = this_month_start - timedelta(seconds=1)
+
+            case "this year":
+                start = datetime(local_now.year, 1, 1, 0, 0, 0, tzinfo=tz)
+                end = datetime(local_now.year, 12, 31, 23, 59, 59, tzinfo=tz)
+
+            case "previous week":
+                days_since_monday = local_now.weekday()
+                this_week_start = datetime.combine(
+                    today - timedelta(days=days_since_monday),
+                    time.min,
+                    tzinfo=tz,
+                )
+                start = this_week_start - timedelta(days=7)
+                end = this_week_start - timedelta(seconds=1)
+
+            case "previous quarter":
+                current_quarter = (local_now.month - 1) // 3 + 1
+                this_quarter_start_month = (current_quarter - 1) * 3 + 1
+                this_quarter_start = datetime(
+                    local_now.year,
+                    this_quarter_start_month,
+                    1,
+                    0,
+                    0,
+                    0,
+                    tzinfo=tz,
+                )
+                start = this_quarter_start - relativedelta(months=3)
+                end = this_quarter_start - timedelta(seconds=1)
+
+            case "previous year":
+                start = datetime(local_now.year - 1, 1, 1, 0, 0, 0, tzinfo=tz)
+                end = datetime(local_now.year - 1, 12, 31, 23, 59, 59, tzinfo=tz)
+
+        # Convert to UTC and format
         start_str = start.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
         end_str = end.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
         return f"{field}:[{start_str} TO {end_str}]"
 
-    return re.sub(pattern, repl, query_string)
+    return re.sub(pattern, repl, query_string, flags=re.IGNORECASE)

src/documents/loggers.py

@@ -3,7 +3,7 @@ import uuid
 
 
 class LoggingMixin:
-    def renew_logging_group(self):
+    def renew_logging_group(self) -> None:
         """
         Creates a new UUID to group subsequent log calls together with
         the extra data named group

src/documents/mail.py

@@ -1,3 +1,6 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
 from email import message_from_bytes
 from pathlib import Path
 
@@ -6,15 +9,31 @@ from django.core.mail import EmailMessage
 from filelock import FileLock
 
 
+@dataclass(frozen=True)
+class EmailAttachment:
+    path: Path
+    mime_type: str
+    friendly_name: str
+
+
 def send_email(
     subject: str,
     body: str,
     to: list[str],
-    attachment: Path | None = None,
-    attachment_mime_type: str | None = None,
+    attachments: list[EmailAttachment],
 ) -> int:
     """
-    Send an email with an optional attachment.
+    Send an email with attachments.
+
+    Args:
+        subject: Email subject
+        body: Email body text
+        to: List of recipient email addresses
+        attachments: List of attachments
+
+    Returns:
+        Number of emails sent
+
     TODO: re-evaluate this pending https://code.djangoproject.com/ticket/35581 / https://github.com/django/django/pull/18966
     """
     email = EmailMessage(
@@ -22,17 +41,46 @@ def send_email(
         body=body,
         to=to,
     )
-    if attachment:
-        # Something could be renaming the file concurrently so it can't be attached
-        with FileLock(settings.MEDIA_LOCK), attachment.open("rb") as f:
-            content = f.read()
-            if attachment_mime_type == "message/rfc822":
-                # See https://forum.djangoproject.com/t/using-emailmessage-with-an-attached-email-file-crashes-due-to-non-ascii/37981
-                content = message_from_bytes(f.read())
 
-            email.attach(
-                filename=attachment.name,
-                content=content,
-                mimetype=attachment_mime_type,
+    used_filenames: set[str] = set()
+
+    # Something could be renaming the file concurrently so it can't be attached
+    with FileLock(settings.MEDIA_LOCK):
+        for attachment in attachments:
+            filename = _get_unique_filename(
+                attachment.friendly_name,
+                used_filenames,
             )
+            used_filenames.add(filename)
+
+            with attachment.path.open("rb") as f:
+                content = f.read()
+                if attachment.mime_type == "message/rfc822":
+                    # See https://forum.djangoproject.com/t/using-emailmessage-with-an-attached-email-file-crashes-due-to-non-ascii/37981
+                    content = message_from_bytes(content)
+
+                email.attach(
+                    filename=filename,
+                    content=content,
+                    mimetype=attachment.mime_type,
+                )
+
     return email.send()
+
+
+def _get_unique_filename(friendly_name: str, used_names: set[str]) -> str:
+    """
+    Constructs a unique friendly filename for the given document, append a counter if needed.
+    """
+    if friendly_name not in used_names:
+        return friendly_name
+
+    stem = Path(friendly_name).stem
+    suffix = "".join(Path(friendly_name).suffixes)
+
+    counter = 1
+    while True:
+        filename = f"{stem}_{counter:02}{suffix}"
+        if filename not in used_names:
+            return filename
+        counter += 1

src/documents/management/commands/convert_mariadb_uuid.py

@@ -9,7 +9,7 @@ class Command(BaseCommand):
     # This code is taken almost entirely from https://github.com/wagtail/wagtail/pull/11912 with all credit to the original author.
     help = "Converts UUID columns from char type to the native UUID type used in MariaDB 10.7+ and Django 5.0+."
 
-    def convert_field(self, model, field_name, *, null=False):
+    def convert_field(self, model, field_name, *, null=False) -> None:
         if model._meta.get_field(field_name).model != model:  # pragma: no cover
             # Field is inherited from a parent model
             return

src/documents/management/commands/decrypt_documents.py

@@ -1,93 +0,0 @@
-from pathlib import Path
-
-from django.conf import settings
-from django.core.management.base import BaseCommand
-from django.core.management.base import CommandError
-
-from documents.models import Document
-from paperless.db import GnuPG
-
-
-class Command(BaseCommand):
-    help = (
-        "This is how you migrate your stored documents from an encrypted "
-        "state to an unencrypted one (or vice-versa)"
-    )
-
-    def add_arguments(self, parser) -> None:
-        parser.add_argument(
-            "--passphrase",
-            help=(
-                "If PAPERLESS_PASSPHRASE isn't set already, you need to specify it here"
-            ),
-        )
-
-    def handle(self, *args, **options) -> None:
-        try:
-            self.stdout.write(
-                self.style.WARNING(
-                    "\n\n"
-                    "WARNING: This script is going to work directly on your "
-                    "document originals, so\n"
-                    "WARNING: you probably shouldn't run "
-                    "this unless you've got a recent backup\n"
-                    "WARNING: handy.  It "
-                    "*should* work without a hitch, but be safe and backup your\n"
-                    "WARNING: stuff first.\n\n"
-                    "Hit Ctrl+C to exit now, or Enter to "
-                    "continue.\n\n",
-                ),
-            )
-            _ = input()
-        except KeyboardInterrupt:
-            return
-
-        passphrase = options["passphrase"] or settings.PASSPHRASE
-        if not passphrase:
-            raise CommandError(
-                "Passphrase not defined.  Please set it with --passphrase or "
-                "by declaring it in your environment or your config.",
-            )
-
-        self.__gpg_to_unencrypted(passphrase)
-
-    def __gpg_to_unencrypted(self, passphrase: str) -> None:
-        encrypted_files = Document.objects.filter(
-            storage_type=Document.STORAGE_TYPE_GPG,
-        )
-
-        for document in encrypted_files:
-            self.stdout.write(f"Decrypting {document}")
-
-            old_paths = [document.source_path, document.thumbnail_path]
-
-            with document.source_file as file_handle:
-                raw_document = GnuPG.decrypted(file_handle, passphrase)
-            with document.thumbnail_file as file_handle:
-                raw_thumb = GnuPG.decrypted(file_handle, passphrase)
-
-            document.storage_type = Document.STORAGE_TYPE_UNENCRYPTED
-
-            ext: str = Path(document.filename).suffix
-
-            if not ext == ".gpg":
-                raise CommandError(
-                    f"Abort: encrypted file {document.source_path} does not "
-                    f"end with .gpg",
-                )
-
-            document.filename = Path(document.filename).stem
-
-            with document.source_path.open("wb") as f:
-                f.write(raw_document)
-
-            with document.thumbnail_path.open("wb") as f:
-                f.write(raw_thumb)
-
-            Document.objects.filter(id=document.id).update(
-                storage_type=document.storage_type,
-                filename=document.filename,
-            )
-
-            for path in old_paths:
-                path.unlink()

src/documents/management/commands/document_consumer.py

@@ -1,128 +1,343 @@
+"""
+Document consumer management command.
+
+Watches a consumption directory for new documents and queues them for processing.
+Uses watchfiles for efficient file system monitoring with support for both
+native OS notifications and polling fallback.
+"""
+
+from __future__ import annotations
+
 import logging
-import os
-from concurrent.futures import ThreadPoolExecutor
-from fnmatch import filter
+from dataclasses import dataclass
 from pathlib import Path
-from pathlib import PurePath
 from threading import Event
 from time import monotonic
-from time import sleep
+from typing import TYPE_CHECKING
 from typing import Final
 
 from django import db
 from django.conf import settings
 from django.core.management.base import BaseCommand
 from django.core.management.base import CommandError
-from watchdog.events import FileSystemEventHandler
-from watchdog.observers.polling import PollingObserver
+from watchfiles import Change
+from watchfiles import DefaultFilter
+from watchfiles import watch
 
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from documents.models import Tag
-from documents.parsers import is_file_ext_supported
+from documents.parsers import get_supported_file_extensions
 from documents.tasks import consume_file
 
-try:
-    from inotifyrecursive import INotify
-    from inotifyrecursive import flags
-except ImportError:  # pragma: no cover
-    INotify = flags = None
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
 
 logger = logging.getLogger("paperless.management.consumer")
 
 
-def _tags_from_path(filepath: Path) -> list[int]:
+@dataclass
+class TrackedFile:
+    """Represents a file being tracked for stability."""
+
+    path: Path
+    last_event_time: float
+    last_mtime: float | None = None
+    last_size: int | None = None
+
+    def update_stats(self) -> bool:
+        """
+        Update file stats. Returns True if file exists and stats were updated.
+        """
+        try:
+            stat = self.path.stat()
+            self.last_mtime = stat.st_mtime
+            self.last_size = stat.st_size
+            return True
+        except OSError:
+            return False
+
+    def is_unchanged(self) -> bool:
+        """
+        Check if file stats match the previously recorded values.
+        Returns False if file doesn't exist or stats changed.
+        """
+        try:
+            stat = self.path.stat()
+            return stat.st_mtime == self.last_mtime and stat.st_size == self.last_size
+        except OSError:
+            return False
+
+
+class FileStabilityTracker:
     """
-    Walk up the directory tree from filepath to CONSUMPTION_DIR
+    Tracks file events and determines when files are stable for consumption.
+
+    A file is considered stable when:
+    1. No new events have been received for it within the stability delay
+    2. Its size and modification time haven't changed
+    3. It still exists as a regular file
+
+    This handles various edge cases:
+    - Network copies that write in chunks
+    - Scanners that open/close files multiple times
+    - Temporary files that get renamed
+    - Files that are deleted before becoming stable
+    """
+
+    def __init__(self, stability_delay: float = 1.0) -> None:
+        """
+        Initialize the tracker.
+
+        Args:
+            stability_delay: Time in seconds a file must remain unchanged
+                           before being considered stable.
+        """
+        self.stability_delay = stability_delay
+        self._tracked: dict[Path, TrackedFile] = {}
+
+    def track(self, path: Path, change: Change) -> None:
+        """
+        Register a file event.
+
+        Args:
+            path: The file path that changed.
+            change: The type of change (added, modified, deleted).
+        """
+        path = path.resolve()
+
+        match change:
+            case Change.deleted:
+                self._tracked.pop(path, None)
+                logger.debug(f"Stopped tracking deleted file: {path}")
+            case Change.added | Change.modified:
+                current_time = monotonic()
+                if path in self._tracked:
+                    tracked = self._tracked[path]
+                    tracked.last_event_time = current_time
+                    tracked.update_stats()
+                    logger.debug(f"Updated tracking for: {path}")
+                else:
+                    tracked = TrackedFile(path=path, last_event_time=current_time)
+                    if tracked.update_stats():
+                        self._tracked[path] = tracked
+                        logger.debug(f"Started tracking: {path}")
+                    else:
+                        logger.debug(f"Could not stat file, not tracking: {path}")
+
+    def get_stable_files(self) -> Iterator[Path]:
+        """
+        Yield files that have been stable for the configured delay.
+
+        Files are removed from tracking once yielded or determined to be invalid.
+        """
+        current_time = monotonic()
+        to_remove: list[Path] = []
+        to_yield: list[Path] = []
+
+        for path, tracked in self._tracked.items():
+            time_since_event = current_time - tracked.last_event_time
+
+            if time_since_event < self.stability_delay:
+                continue
+
+            # File has waited long enough, verify it's unchanged
+            if not tracked.is_unchanged():
+                # Stats changed or file gone - update and wait again
+                if tracked.update_stats():
+                    tracked.last_event_time = current_time
+                    logger.debug(f"File changed during stability check: {path}")
+                else:
+                    # File no longer exists, remove from tracking
+                    to_remove.append(path)
+                    logger.debug(f"File disappeared during stability check: {path}")
+                continue
+
+            # File is stable, we can return it
+            to_yield.append(path)
+            logger.info(f"File is stable: {path}")
+
+        # Remove files that are no longer valid
+        for path in to_remove:
+            self._tracked.pop(path, None)
+
+        # Remove and yield stable files
+        for path in to_yield:
+            self._tracked.pop(path, None)
+            yield path
+
+    def has_pending_files(self) -> bool:
+        """Check if there are files waiting for stability check."""
+        return len(self._tracked) > 0
+
+    @property
+    def pending_count(self) -> int:
+        """Number of files being tracked."""
+        return len(self._tracked)
+
+
+class ConsumerFilter(DefaultFilter):
+    """
+    Filter for watchfiles that accepts only supported document types
+    and ignores system files/directories.
+
+    Extends DefaultFilter leveraging its built-in filtering:
+    - `ignore_dirs`: Directory names to ignore (and all their contents)
+    - `ignore_entity_patterns`: Regex patterns matched against filename/dirname only
+
+    We add custom logic for file extension filtering (only accept supported
+    document types), which the library doesn't provide.
+    """
+
+    # Regex patterns for files to always ignore (matched against filename only)
+    # These are passed to DefaultFilter.ignore_entity_patterns
+    DEFAULT_IGNORE_PATTERNS: Final[tuple[str, ...]] = (
+        r"^\.DS_Store$",
+        r"^\.DS_STORE$",
+        r"^\._.*",
+        r"^desktop\.ini$",
+        r"^Thumbs\.db$",
+    )
+
+    # Directories to always ignore (passed to DefaultFilter.ignore_dirs)
+    # These are matched by directory name, not full path
+    DEFAULT_IGNORE_DIRS: Final[tuple[str, ...]] = (
+        ".stfolder",  # Syncthing
+        ".stversions",  # Syncthing
+        ".localized",  # macOS
+        "@eaDir",  # Synology NAS
+        ".Spotlight-V100",  # macOS
+        ".Trashes",  # macOS
+        "__MACOSX",  # macOS archive artifacts
+    )
+
+    def __init__(
+        self,
+        *,
+        supported_extensions: frozenset[str] | None = None,
+        ignore_patterns: list[str] | None = None,
+        ignore_dirs: list[str] | None = None,
+    ) -> None:
+        """
+        Initialize the consumer filter.
+
+        Args:
+            supported_extensions: Set of file extensions to accept (e.g., {".pdf", ".png"}).
+                If None, uses get_supported_file_extensions().
+            ignore_patterns: Additional regex patterns to ignore (matched against filename).
+            ignore_dirs: Additional directory names to ignore (merged with defaults).
+        """
+        # Get supported extensions
+        if supported_extensions is None:
+            supported_extensions = frozenset(get_supported_file_extensions())
+        self._supported_extensions = supported_extensions
+
+        # Combine default and user patterns
+        all_patterns: list[str] = list(self.DEFAULT_IGNORE_PATTERNS)
+        if ignore_patterns:
+            all_patterns.extend(ignore_patterns)
+
+        # Combine default and user ignore_dirs
+        all_ignore_dirs: list[str] = list(self.DEFAULT_IGNORE_DIRS)
+        if ignore_dirs:
+            all_ignore_dirs.extend(ignore_dirs)
+
+        # Let DefaultFilter handle all the pattern and directory filtering
+        super().__init__(
+            ignore_dirs=tuple(all_ignore_dirs),
+            ignore_entity_patterns=tuple(all_patterns),
+            ignore_paths=(),
+        )
+
+    def __call__(self, change: Change, path: str) -> bool:
+        """
+        Filter function for watchfiles.
+
+        Returns True if the path should be watched, False to ignore.
+
+        The parent DefaultFilter handles:
+        - Hidden files/directories (starting with .)
+        - Directories in ignore_dirs
+        - Files/directories matching ignore_entity_patterns
+
+        We additionally filter files by extension.
+        """
+        # Let parent filter handle directory ignoring and pattern matching
+        if not super().__call__(change, path):
+            return False
+
+        path_obj = Path(path)
+
+        # For directories, parent filter already handled everything
+        if path_obj.is_dir():
+            return True
+
+        # For files, check extension
+        return self._has_supported_extension(path_obj)
+
+    def _has_supported_extension(self, path: Path) -> bool:
+        """Check if the file has a supported extension."""
+        suffix = path.suffix.lower()
+        return suffix in self._supported_extensions
+
+
+def _tags_from_path(filepath: Path, consumption_dir: Path) -> list[int]:
+    """
+    Walk up the directory tree from filepath to consumption_dir
     and get or create Tag IDs for every directory.
 
-    Returns set of Tag models
+    Returns list of Tag primary keys.
     """
     db.close_old_connections()
-    tag_ids = set()
-    path_parts = filepath.relative_to(settings.CONSUMPTION_DIR).parent.parts
+    tag_ids: set[int] = set()
+    path_parts = filepath.relative_to(consumption_dir).parent.parts
+
     for part in path_parts:
-        tag_ids.add(
-            Tag.objects.get_or_create(name__iexact=part, defaults={"name": part})[0].pk,
+        tag, _ = Tag.objects.get_or_create(
+            name__iexact=part,
+            defaults={"name": part},
         )
+        tag_ids.add(tag.pk)
 
     return list(tag_ids)
 
 
-def _is_ignored(filepath: Path) -> bool:
+def _consume_file(
+    filepath: Path,
+    consumption_dir: Path,
+    *,
+    subdirs_as_tags: bool,
+) -> None:
     """
-    Checks if the given file should be ignored, based on configured
-    patterns.
+    Queue a file for consumption.
 
-    Returns True if the file is ignored, False otherwise
+    Args:
+        filepath: Path to the file to consume.
+        consumption_dir: Base consumption directory.
+        subdirs_as_tags: Whether to create tags from subdirectory names.
     """
-    # Trim out the consume directory, leaving only filename and it's
-    # path relative to the consume directory
-    filepath_relative = PurePath(filepath).relative_to(settings.CONSUMPTION_DIR)
-
-    # March through the components of the path, including directories and the filename
-    # looking for anything matching
-    # foo/bar/baz/file.pdf -> (foo, bar, baz, file.pdf)
-    parts = []
-    for part in filepath_relative.parts:
-        # If the part is not the name (ie, it's a dir)
-        # Need to append the trailing slash or fnmatch doesn't match
-        # fnmatch("dir", "dir/*") == False
-        # fnmatch("dir/", "dir/*") == True
-        if part != filepath_relative.name:
-            part = part + "/"
-        parts.append(part)
-
-    for pattern in settings.CONSUMER_IGNORE_PATTERNS:
-        if len(filter(parts, pattern)):
-            return True
-
-    return False
-
-
-def _consume(filepath: Path) -> None:
-    if filepath.is_dir() or _is_ignored(filepath):
+    # Verify file still exists and is accessible
+    try:
+        if not filepath.is_file():
+            logger.debug(f"Not consuming {filepath}: not a file or doesn't exist")
+            return
+    except OSError as e:
+        logger.warning(f"Not consuming {filepath}: {e}")
         return
 
-    if not filepath.is_file():
-        logger.debug(f"Not consuming file {filepath}: File has moved.")
-        return
-
-    if not is_file_ext_supported(filepath.suffix):
-        logger.warning(f"Not consuming file {filepath}: Unknown file extension.")
-        return
-
-    # Total wait time: up to 500ms
-    os_error_retry_count: Final[int] = 50
-    os_error_retry_wait: Final[float] = 0.01
-
-    read_try_count = 0
-    file_open_ok = False
-    os_error_str = None
-
-    while (read_try_count < os_error_retry_count) and not file_open_ok:
+    # Get tags from path if configured
+    tag_ids: list[int] | None = None
+    if subdirs_as_tags:
         try:
-            with filepath.open("rb"):
-                file_open_ok = True
-        except OSError as e:
-            read_try_count += 1
-            os_error_str = str(e)
-            sleep(os_error_retry_wait)
+            tag_ids = _tags_from_path(filepath, consumption_dir)
+        except Exception:
+            logger.exception(f"Error creating tags from path for {filepath}")
 
-    if read_try_count >= os_error_retry_count:
-        logger.warning(f"Not consuming file {filepath}: OS reports {os_error_str}")
-        return
-
-    tag_ids = None
+    # Queue for consumption
     try:
-        if settings.CONSUMER_SUBDIRS_AS_TAGS:
-            tag_ids = _tags_from_path(filepath)
-    except Exception:
-        logger.exception("Error creating tags from path")
-
-    try:
-        logger.info(f"Adding {filepath} to the task queue.")
+        logger.info(f"Adding {filepath} to the task queue")
         consume_file.delay(
             ConsumableDocument(
                 source=DocumentSource.ConsumeFolder,
@@ -131,223 +346,228 @@ def _consume(filepath: Path) -> None:
             DocumentMetadataOverrides(tag_ids=tag_ids),
         )
     except Exception:
-        # Catch all so that the consumer won't crash.
-        # This is also what the test case is listening for to check for
-        # errors.
-        logger.exception("Error while consuming document")
-
-
-def _consume_wait_unmodified(file: Path) -> None:
-    """
-    Waits for the given file to appear unmodified based on file size
-    and modification time.  Will wait a configured number of seconds
-    and retry a configured number of times before either consuming or
-    giving up
-    """
-    if _is_ignored(file):
-        return
-
-    logger.debug(f"Waiting for file {file} to remain unmodified")
-    mtime = -1
-    size = -1
-    current_try = 0
-    while current_try < settings.CONSUMER_POLLING_RETRY_COUNT:
-        try:
-            stat_data = file.stat()
-            new_mtime = stat_data.st_mtime
-            new_size = stat_data.st_size
-        except FileNotFoundError:
-            logger.debug(
-                f"File {file} moved while waiting for it to remain unmodified.",
-            )
-            return
-        if new_mtime == mtime and new_size == size:
-            _consume(file)
-            return
-        mtime = new_mtime
-        size = new_size
-        sleep(settings.CONSUMER_POLLING_DELAY)
-        current_try += 1
-
-    logger.error(f"Timeout while waiting on file {file} to remain unmodified.")
-
-
-class Handler(FileSystemEventHandler):
-    def __init__(self, pool: ThreadPoolExecutor) -> None:
-        super().__init__()
-        self._pool = pool
-
-    def on_created(self, event):
-        self._pool.submit(_consume_wait_unmodified, Path(event.src_path))
-
-    def on_moved(self, event):
-        self._pool.submit(_consume_wait_unmodified, Path(event.dest_path))
+        logger.exception(f"Error while queuing document {filepath}")
 
 
 class Command(BaseCommand):
     """
-    On every iteration of an infinite loop, consume what we can from the
-    consumption directory.
+    Watch a consumption directory and queue new documents for processing.
+
+    Uses watchfiles for efficient file system monitoring. Supports both
+    native OS notifications (inotify on Linux, FSEvents on macOS) and
+    polling for network filesystems.
     """
 
-    # This is here primarily for the tests and is irrelevant in production.
-    stop_flag = Event()
-    # Also only for testing, configures in one place the timeout used before checking
-    # the stop flag
-    testing_timeout_s: Final[float] = 0.5
-    testing_timeout_ms: Final[float] = testing_timeout_s * 1000.0
+    help = "Watch the consumption directory for new documents"
 
-    def add_arguments(self, parser):
+    # For testing - allows tests to stop the consumer
+    stop_flag: Event = Event()
+
+    # Testing timeout in seconds
+    testing_timeout_s: Final[float] = 0.5
+
+    def add_arguments(self, parser) -> None:
         parser.add_argument(
             "directory",
-            default=settings.CONSUMPTION_DIR,
+            default=None,
             nargs="?",
-            help="The consumption directory.",
+            help="The consumption directory (defaults to CONSUMPTION_DIR setting)",
+        )
+        parser.add_argument(
+            "--oneshot",
+            action="store_true",
+            help="Process existing files and exit without watching",
         )
-        parser.add_argument("--oneshot", action="store_true", help="Run only once.")
-
-        # Only use during unit testing, will configure a timeout
-        # Leaving it unset or false and the consumer will exit when it
-        # receives SIGINT
         parser.add_argument(
             "--testing",
             action="store_true",
-            help="Flag used only for unit testing",
+            help="Enable testing mode with shorter timeouts",
             default=False,
         )
 
-    def handle(self, *args, **options):
-        directory = options["directory"]
-        recursive = settings.CONSUMER_RECURSIVE
-
+    def handle(self, *args, **options) -> None:
+        # Resolve consumption directory
+        directory = options.get("directory")
         if not directory:
-            raise CommandError("CONSUMPTION_DIR does not appear to be set.")
+            directory = getattr(settings, "CONSUMPTION_DIR", None)
+        if not directory:
+            raise CommandError("CONSUMPTION_DIR is not configured")
 
         directory = Path(directory).resolve()
 
-        if not directory.is_dir():
-            raise CommandError(f"Consumption directory {directory} does not exist")
+        if not directory.exists():
+            raise CommandError(f"Consumption directory does not exist: {directory}")
 
-        # Consumer will need this
+        if not directory.is_dir():
+            raise CommandError(f"Consumption path is not a directory: {directory}")
+
+        # Ensure scratch directory exists
         settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
 
-        if recursive:
-            for dirpath, _, filenames in os.walk(directory):
-                for filename in filenames:
-                    filepath = Path(dirpath) / filename
-                    _consume(filepath)
-        else:
-            for filepath in directory.iterdir():
-                _consume(filepath)
+        # Get settings
+        recursive: bool = settings.CONSUMER_RECURSIVE
+        subdirs_as_tags: bool = settings.CONSUMER_SUBDIRS_AS_TAGS
+        polling_interval: float = settings.CONSUMER_POLLING_INTERVAL
+        stability_delay: float = settings.CONSUMER_STABILITY_DELAY
+        ignore_patterns: list[str] = settings.CONSUMER_IGNORE_PATTERNS
+        ignore_dirs: list[str] = settings.CONSUMER_IGNORE_DIRS
+        is_testing: bool = options.get("testing", False)
+        is_oneshot: bool = options.get("oneshot", False)
 
-        if options["oneshot"]:
+        # Create filter
+        consumer_filter = ConsumerFilter(
+            ignore_patterns=ignore_patterns,
+            ignore_dirs=ignore_dirs,
+        )
+
+        # Process existing files
+        self._process_existing_files(
+            directory=directory,
+            recursive=recursive,
+            subdirs_as_tags=subdirs_as_tags,
+            consumer_filter=consumer_filter,
+        )
+
+        if is_oneshot:
+            logger.info("Oneshot mode: processed existing files, exiting")
             return
 
-        if settings.CONSUMER_POLLING == 0 and INotify:
-            self.handle_inotify(directory, recursive, is_testing=options["testing"])
+        # Start watching
+        self._watch_directory(
+            directory=directory,
+            recursive=recursive,
+            subdirs_as_tags=subdirs_as_tags,
+            consumer_filter=consumer_filter,
+            polling_interval=polling_interval,
+            stability_delay=stability_delay,
+            is_testing=is_testing,
+        )
+
+        logger.debug("Consumer exiting")
+
+    def _process_existing_files(
+        self,
+        *,
+        directory: Path,
+        recursive: bool,
+        subdirs_as_tags: bool,
+        consumer_filter: ConsumerFilter,
+    ) -> None:
+        """Process any existing files in the consumption directory."""
+        logger.info(f"Processing existing files in {directory}")
+
+        glob_pattern = "**/*" if recursive else "*"
+
+        for filepath in directory.glob(glob_pattern):
+            # Use filter to check if file should be processed
+            if not filepath.is_file():
+                continue
+
+            if not consumer_filter(Change.added, str(filepath)):
+                continue
+
+            _consume_file(
+                filepath=filepath,
+                consumption_dir=directory,
+                subdirs_as_tags=subdirs_as_tags,
+            )
+
+    def _watch_directory(
+        self,
+        *,
+        directory: Path,
+        recursive: bool,
+        subdirs_as_tags: bool,
+        consumer_filter: ConsumerFilter,
+        polling_interval: float,
+        stability_delay: float,
+        is_testing: bool,
+    ) -> None:
+        """Watch directory for changes and process stable files."""
+        use_polling = polling_interval > 0
+        poll_delay_ms = int(polling_interval * 1000) if use_polling else 0
+
+        if use_polling:
+            logger.info(
+                f"Watching {directory} using polling (interval: {polling_interval}s)",
+            )
         else:
-            if INotify is None and settings.CONSUMER_POLLING == 0:  # pragma: no cover
-                logger.warning("Using polling as INotify import failed")
-            self.handle_polling(directory, recursive, is_testing=options["testing"])
+            logger.info(f"Watching {directory} using native file system events")
 
-        logger.debug("Consumer exiting.")
+        # Create stability tracker
+        tracker = FileStabilityTracker(stability_delay=stability_delay)
 
-    def handle_polling(self, directory, recursive, *, is_testing: bool):
-        logger.info(f"Polling directory for changes: {directory}")
+        # Calculate timeouts
+        stability_timeout_ms = int(stability_delay * 1000)
+        testing_timeout_ms = int(self.testing_timeout_s * 1000)
 
-        timeout = None
+        # Calculate appropriate timeout for watch loop
+        # In polling mode, rust_timeout must be significantly longer than poll_delay_ms
+        # to ensure poll cycles can complete before timing out
         if is_testing:
-            timeout = self.testing_timeout_s
-            logger.debug(f"Configuring timeout to {timeout}s")
+            if use_polling:
+                # For polling: timeout must be at least 3x the poll interval to allow
+                # multiple poll cycles. This prevents timeouts from interfering with
+                # the polling mechanism.
+                min_polling_timeout_ms = poll_delay_ms * 3
+                timeout_ms = max(min_polling_timeout_ms, testing_timeout_ms)
+            else:
+                # For native watching, use short timeout to check stop flag
+                timeout_ms = testing_timeout_ms
+        else:
+            # Not testing, wait indefinitely for first event
+            timeout_ms = 0
 
-        polling_interval = settings.CONSUMER_POLLING
-        if polling_interval == 0:  # pragma: no cover
-            # Only happens if INotify failed to import
-            logger.warning("Using polling of 10s, consider setting this")
-            polling_interval = 10
+        self.stop_flag.clear()
 
-        with ThreadPoolExecutor(max_workers=4) as pool:
-            observer = PollingObserver(timeout=polling_interval)
-            observer.schedule(Handler(pool), directory, recursive=recursive)
-            observer.start()
+        while not self.stop_flag.is_set():
             try:
-                while observer.is_alive():
-                    observer.join(timeout)
-                    if self.stop_flag.is_set():
-                        observer.stop()
-            except KeyboardInterrupt:
-                observer.stop()
-            observer.join()
+                for changes in watch(
+                    directory,
+                    watch_filter=consumer_filter,
+                    rust_timeout=timeout_ms,
+                    yield_on_timeout=True,
+                    force_polling=use_polling,
+                    poll_delay_ms=poll_delay_ms,
+                    recursive=recursive,
+                    stop_event=self.stop_flag,
+                ):
+                    # Process each change
+                    for change_type, path in changes:
+                        path = Path(path).resolve()
+                        if not path.is_file():
+                            continue
+                        logger.debug(f"Event: {change_type.name} for {path}")
+                        tracker.track(path, change_type)
 
-    def handle_inotify(self, directory, recursive, *, is_testing: bool):
-        logger.info(f"Using inotify to watch directory for changes: {directory}")
+                    # Check for stable files
+                    for stable_path in tracker.get_stable_files():
+                        _consume_file(
+                            filepath=stable_path,
+                            consumption_dir=directory,
+                            subdirs_as_tags=subdirs_as_tags,
+                        )
 
-        timeout_ms = None
-        if is_testing:
-            timeout_ms = self.testing_timeout_ms
-            logger.debug(f"Configuring timeout to {timeout_ms}ms")
+                    # Exit watch loop to reconfigure timeout
+                    break
 
-        inotify = INotify()
-        inotify_flags = flags.CLOSE_WRITE | flags.MOVED_TO | flags.MODIFY
-        if recursive:
-            inotify.add_watch_recursive(directory, inotify_flags)
-        else:
-            inotify.add_watch(directory, inotify_flags)
-
-        inotify_debounce_secs: Final[float] = settings.CONSUMER_INOTIFY_DELAY
-        inotify_debounce_ms: Final[int] = inotify_debounce_secs * 1000
-
-        finished = False
-
-        notified_files = {}
-
-        try:
-            while not finished:
-                try:
-                    for event in inotify.read(timeout=timeout_ms):
-                        path = inotify.get_path(event.wd) if recursive else directory
-                        filepath = Path(path) / event.name
-                        if flags.MODIFY in flags.from_mask(event.mask):
-                            notified_files.pop(filepath, None)
-                        else:
-                            notified_files[filepath] = monotonic()
-
-                    # Check the files against the timeout
-                    still_waiting = {}
-                    # last_event_time is time of the last inotify event for this file
-                    for filepath, last_event_time in notified_files.items():
-                        # Current time - last time over the configured timeout
-                        waited_long_enough = (
-                            monotonic() - last_event_time
-                        ) > inotify_debounce_secs
-
-                        # Also make sure the file exists still, some scanners might write a
-                        # temporary file first
-                        file_still_exists = filepath.exists() and filepath.is_file()
-
-                        if waited_long_enough and file_still_exists:
-                            _consume(filepath)
-                        elif file_still_exists:
-                            still_waiting[filepath] = last_event_time
-
-                    # These files are still waiting to hit the timeout
-                    notified_files = still_waiting
-
-                    # If files are waiting, need to exit read() to check them
-                    # Otherwise, go back to infinite sleep time, but only if not testing
-                    if len(notified_files) > 0:
-                        timeout_ms = inotify_debounce_ms
-                    elif is_testing:
-                        timeout_ms = self.testing_timeout_ms
+                # Determine next timeout
+                if tracker.has_pending_files():
+                    # Check pending files at stability interval
+                    timeout_ms = stability_timeout_ms
+                elif is_testing:
+                    # In testing, use appropriate timeout based on watch mode
+                    if use_polling:
+                        # For polling: ensure timeout allows polls to complete
+                        min_polling_timeout_ms = poll_delay_ms * 3
+                        timeout_ms = max(min_polling_timeout_ms, testing_timeout_ms)
                     else:
-                        timeout_ms = None
+                        # For native watching, use short timeout to check stop flag
+                        timeout_ms = testing_timeout_ms
+                else:  # pragma: nocover
+                    # No pending files, wait indefinitely
+                    timeout_ms = 0
 
-                    if self.stop_flag.is_set():
-                        logger.debug("Finishing because event is set")
-                        finished = True
-
-                except KeyboardInterrupt:
-                    logger.info("Received SIGINT, stopping inotify")
-                    finished = True
-        finally:
-            inotify.close()
+            except KeyboardInterrupt:  # pragma: nocover
+                logger.info("Received interrupt, stopping consumer")
+                self.stop_flag.set()

src/documents/management/commands/document_exporter.py

@@ -3,7 +3,6 @@ import json
 import os
 import shutil
 import tempfile
-import time
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -56,7 +55,6 @@ from documents.settings import EXPORTER_FILE_NAME
 from documents.settings import EXPORTER_THUMBNAIL_NAME
 from documents.utils import copy_file_with_basic_stats
 from paperless import version
-from paperless.db import GnuPG
 from paperless.models import ApplicationConfiguration
 from paperless_mail.models import MailAccount
 from paperless_mail.models import MailRule
@@ -69,7 +67,7 @@ class Command(CryptMixin, BaseCommand):
         "easy import."
     )
 
-    def add_arguments(self, parser):
+    def add_arguments(self, parser) -> None:
         parser.add_argument("target")
 
         parser.add_argument(
@@ -188,7 +186,7 @@ class Command(CryptMixin, BaseCommand):
             help="If provided, is used to encrypt sensitive data in the export",
         )
 
-    def handle(self, *args, **options):
+    def handle(self, *args, **options) -> None:
         self.target = Path(options["target"]).resolve()
         self.split_manifest: bool = options["split_manifest"]
         self.compare_checksums: bool = options["compare_checksums"]
@@ -246,7 +244,7 @@ class Command(CryptMixin, BaseCommand):
             if self.zip_export and temp_dir is not None:
                 temp_dir.cleanup()
 
-    def dump(self):
+    def dump(self) -> None:
         # 1. Take a snapshot of what files exist in the current export folder
         for x in self.target.glob("**/*"):
             if x.is_file():
@@ -316,20 +314,17 @@ class Command(CryptMixin, BaseCommand):
             total=len(document_manifest),
             disable=self.no_progress_bar,
         ):
-            # 3.1. store files unencrypted
-            document_dict["fields"]["storage_type"] = Document.STORAGE_TYPE_UNENCRYPTED
-
             document = document_map[document_dict["pk"]]
 
-            # 3.2. generate a unique filename
+            # 3.1. generate a unique filename
             base_name = self.generate_base_name(document)
 
-            # 3.3. write filenames into manifest
+            # 3.2. write filenames into manifest
             original_target, thumbnail_target, archive_target = (
                 self.generate_document_targets(document, base_name, document_dict)
             )
 
-            # 3.4. write files to target folder
+            # 3.3. write files to target folder
             if not self.data_only:
                 self.copy_document_files(
                     document,
@@ -423,7 +418,6 @@ class Command(CryptMixin, BaseCommand):
                 base_name = generate_filename(
                     document,
                     counter=filename_counter,
-                    append_gpg=False,
                 )
             else:
                 base_name = document.get_public_filename(counter=filename_counter)
@@ -482,51 +476,29 @@ class Command(CryptMixin, BaseCommand):
 
         If the document is encrypted, the files are decrypted before copying them to the target location.
         """
-        if document.storage_type == Document.STORAGE_TYPE_GPG:
-            t = int(time.mktime(document.created.timetuple()))
+        self.check_and_copy(
+            document.source_path,
+            document.checksum,
+            original_target,
+        )
 
-            original_target.parent.mkdir(parents=True, exist_ok=True)
-            with document.source_file as out_file:
-                original_target.write_bytes(GnuPG.decrypted(out_file))
-                os.utime(original_target, times=(t, t))
+        if thumbnail_target:
+            self.check_and_copy(document.thumbnail_path, None, thumbnail_target)
 
-            if thumbnail_target:
-                thumbnail_target.parent.mkdir(parents=True, exist_ok=True)
-                with document.thumbnail_file as out_file:
-                    thumbnail_target.write_bytes(GnuPG.decrypted(out_file))
-                    os.utime(thumbnail_target, times=(t, t))
-
-            if archive_target:
-                archive_target.parent.mkdir(parents=True, exist_ok=True)
-                if TYPE_CHECKING:
-                    assert isinstance(document.archive_path, Path)
-                with document.archive_path as out_file:
-                    archive_target.write_bytes(GnuPG.decrypted(out_file))
-                    os.utime(archive_target, times=(t, t))
-        else:
+        if archive_target:
+            if TYPE_CHECKING:
+                assert isinstance(document.archive_path, Path)
             self.check_and_copy(
-                document.source_path,
-                document.checksum,
-                original_target,
+                document.archive_path,
+                document.archive_checksum,
+                archive_target,
             )
 
-            if thumbnail_target:
-                self.check_and_copy(document.thumbnail_path, None, thumbnail_target)
-
-            if archive_target:
-                if TYPE_CHECKING:
-                    assert isinstance(document.archive_path, Path)
-                self.check_and_copy(
-                    document.archive_path,
-                    document.archive_checksum,
-                    archive_target,
-                )
-
     def check_and_write_json(
         self,
         content: list[dict] | dict,
         target: Path,
-    ):
+    ) -> None:
         """
         Writes the source content to the target json file.
         If --compare-json arg was used, don't write to target file if
@@ -556,7 +528,7 @@ class Command(CryptMixin, BaseCommand):
         source: Path,
         source_checksum: str | None,
         target: Path,
-    ):
+    ) -> None:
         """
         Copies the source to the target, if target doesn't exist or the target doesn't seem to match
         the source attributes

src/documents/management/commands/document_fuzzy_match.py

@@ -92,6 +92,9 @@ class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
                 # doc to doc is obviously not useful
                 if first_doc.pk == second_doc.pk:
                     continue
+                # Skip empty documents (e.g. password-protected)
+                if first_doc.content.strip() == "" or second_doc.content.strip() == "":
+                    continue
                 # Skip matching which have already been matched together
                 # doc 1 to doc 2 is the same as doc 2 to doc 1
                 doc_1_to_doc_2 = (first_doc.pk, second_doc.pk)

src/documents/management/commands/document_importer.py

@@ -48,12 +48,13 @@ if settings.AUDIT_LOG_ENABLED:
 
 
 @contextmanager
-def disable_signal(sig, receiver, sender) -> Generator:
+def disable_signal(sig, receiver, sender, *, weak: bool | None = None) -> Generator:
     try:
         sig.disconnect(receiver=receiver, sender=sender)
         yield
     finally:
-        sig.connect(receiver=receiver, sender=sender)
+        kwargs = {"weak": weak} if weak is not None else {}
+        sig.connect(receiver=receiver, sender=sender, **kwargs)
 
 
 class Command(CryptMixin, BaseCommand):
@@ -245,7 +246,7 @@ class Command(CryptMixin, BaseCommand):
                 self.source = Path(tmp_dir)
             self._run_import()
 
-    def _run_import(self):
+    def _run_import(self) -> None:
         self.pre_check()
         self.load_metadata()
         self.load_manifest_files()
@@ -258,16 +259,19 @@ class Command(CryptMixin, BaseCommand):
                 post_save,
                 receiver=update_filename_and_move_files,
                 sender=Document,
+                weak=False,
             ),
             disable_signal(
                 m2m_changed,
                 receiver=update_filename_and_move_files,
                 sender=Document.tags.through,
+                weak=False,
             ),
             disable_signal(
                 post_save,
                 receiver=update_filename_and_move_files,
                 sender=CustomFieldInstance,
+                weak=False,
             ),
             disable_signal(
                 post_save,
@@ -379,8 +383,6 @@ class Command(CryptMixin, BaseCommand):
             else:
                 archive_path = None
 
-            document.storage_type = Document.STORAGE_TYPE_UNENCRYPTED
-
             with FileLock(settings.MEDIA_LOCK):
                 if Path(document.source_path).is_file():
                     raise FileExistsError(document.source_path)

src/documents/management/commands/document_llmindex.py

@@ -0,0 +1,22 @@
+from django.core.management import BaseCommand
+from django.db import transaction
+
+from documents.management.commands.mixins import ProgressBarMixin
+from documents.tasks import llmindex_index
+
+
+class Command(ProgressBarMixin, BaseCommand):
+    help = "Manages the LLM-based vector index for Paperless."
+
+    def add_arguments(self, parser):
+        parser.add_argument("command", choices=["rebuild", "update"])
+        self.add_argument_progress_bar_mixin(parser)
+
+    def handle(self, *args, **options):
+        self.handle_progress_bar_mixin(**options)
+        with transaction.atomic():
+            llmindex_index(
+                progress_bar_disable=self.no_progress_bar,
+                rebuild=options["command"] == "rebuild",
+                scheduled=False,
+            )

src/documents/management/commands/document_thumbnails.py

@@ -12,7 +12,7 @@ from documents.models import Document
 from documents.parsers import get_parser_class_for_mime_type
 
 
-def _process_document(doc_id):
+def _process_document(doc_id) -> None:
     document: Document = Document.objects.get(id=doc_id)
     parser_class = get_parser_class_for_mime_type(document.mime_type)
 
@@ -37,7 +37,7 @@ def _process_document(doc_id):
 class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
     help = "This will regenerate the thumbnails for all documents."
 
-    def add_arguments(self, parser):
+    def add_arguments(self, parser) -> None:
         parser.add_argument(
             "-d",
             "--document",

src/documents/management/commands/manage_superuser.py

@@ -25,7 +25,7 @@ class Command(BaseCommand):
         parser.formatter_class = RawTextHelpFormatter
         return parser
 
-    def handle(self, *args, **options):
+    def handle(self, *args, **options) -> None:
         username = os.getenv("PAPERLESS_ADMIN_USER", "admin")
         mail = os.getenv("PAPERLESS_ADMIN_MAIL", "root@localhost")
         password = os.getenv("PAPERLESS_ADMIN_PASSWORD")

src/documents/management/commands/mixins.py

@@ -27,7 +27,7 @@ class MultiProcessMixin:
     for the use of multiple processes
     """
 
-    def add_argument_processes_mixin(self, parser: ArgumentParser):
+    def add_argument_processes_mixin(self, parser: ArgumentParser) -> None:
         parser.add_argument(
             "--processes",
             default=max(1, os.cpu_count() // 4),
@@ -35,7 +35,7 @@ class MultiProcessMixin:
             help="Number of processes to distribute work amongst",
         )
 
-    def handle_processes_mixin(self, *args, **options):
+    def handle_processes_mixin(self, *args, **options) -> None:
         self.process_count = options["processes"]
         if self.process_count < 1:
             raise CommandError("There must be at least 1 process")
@@ -47,7 +47,7 @@ class ProgressBarMixin:
     via this class
     """
 
-    def add_argument_progress_bar_mixin(self, parser: ArgumentParser):
+    def add_argument_progress_bar_mixin(self, parser: ArgumentParser) -> None:
         parser.add_argument(
             "--no-progress-bar",
             default=False,
@@ -55,7 +55,7 @@ class ProgressBarMixin:
             help="If set, the progress bar will not be shown",
         )
 
-    def handle_progress_bar_mixin(self, *args, **options):
+    def handle_progress_bar_mixin(self, *args, **options) -> None:
         self.no_progress_bar = options["no_progress_bar"]
         self.use_progress_bar = not self.no_progress_bar
 
@@ -120,7 +120,7 @@ class CryptMixin:
             },
         }
 
-    def load_crypt_params(self, metadata: dict):
+    def load_crypt_params(self, metadata: dict) -> None:
         # Load up the values for setting up decryption
         self.kdf_algorithm: str = metadata[EXPORTER_CRYPTO_SETTINGS_NAME][
             EXPORTER_CRYPTO_ALGO_NAME
@@ -135,7 +135,7 @@ class CryptMixin:
             EXPORTER_CRYPTO_SALT_NAME
         ]
 
-    def setup_crypto(self, *, passphrase: str, salt: str | None = None):
+    def setup_crypto(self, *, passphrase: str, salt: str | None = None) -> None:
         """
         Constructs a class for encryption or decryption using the specified passphrase and salt
 

src/documents/matching.py

@@ -6,8 +6,11 @@ from fnmatch import fnmatch
 from fnmatch import translate as fnmatch_translate
 from typing import TYPE_CHECKING
 
+from rest_framework import serializers
+
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentSource
+from documents.filters import CustomFieldQueryParser
 from documents.models import Correspondent
 from documents.models import Document
 from documents.models import DocumentType
@@ -17,6 +20,7 @@ from documents.models import Tag
 from documents.models import Workflow
 from documents.models import WorkflowTrigger
 from documents.permissions import get_objects_for_user_owner_aware
+from documents.regex import safe_regex_search
 
 if TYPE_CHECKING:
     from django.db.models import QuerySet
@@ -30,7 +34,7 @@ def log_reason(
     matching_model: MatchingModel | WorkflowTrigger,
     document: Document,
     reason: str,
-):
+) -> None:
     class_name = type(matching_model).__name__
     name = (
         matching_model.name if hasattr(matching_model, "name") else str(matching_model)
@@ -61,8 +65,12 @@ def match_correspondents(document: Document, classifier: DocumentClassifier, use
 
     return list(
         filter(
-            lambda o: matches(o, document)
-            or (o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO),
+            lambda o: (
+                matches(o, document)
+                or (
+                    o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO
+                )
+            ),
             correspondents,
         ),
     )
@@ -88,8 +96,12 @@ def match_document_types(document: Document, classifier: DocumentClassifier, use
 
     return list(
         filter(
-            lambda o: matches(o, document)
-            or (o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO),
+            lambda o: (
+                matches(o, document)
+                or (
+                    o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO
+                )
+            ),
             document_types,
         ),
     )
@@ -110,10 +122,12 @@ def match_tags(document: Document, classifier: DocumentClassifier, user=None):
 
     return list(
         filter(
-            lambda o: matches(o, document)
-            or (
-                o.matching_algorithm == MatchingModel.MATCH_AUTO
-                and o.pk in predicted_tag_ids
+            lambda o: (
+                matches(o, document)
+                or (
+                    o.matching_algorithm == MatchingModel.MATCH_AUTO
+                    and o.pk in predicted_tag_ids
+                )
             ),
             tags,
         ),
@@ -141,15 +155,19 @@ def match_storage_paths(document: Document, classifier: DocumentClassifier, user
 
     return list(
         filter(
-            lambda o: matches(o, document)
-            or (o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO),
+            lambda o: (
+                matches(o, document)
+                or (
+                    o.pk == pred_id and o.matching_algorithm == MatchingModel.MATCH_AUTO
+                )
+            ),
             storage_paths,
         ),
     )
 
 
 def matches(matching_model: MatchingModel, document: Document):
-    search_kwargs = {}
+    search_flags = 0
 
     document_content = document.content
 
@@ -158,14 +176,18 @@ def matches(matching_model: MatchingModel, document: Document):
         return False
 
     if matching_model.is_insensitive:
-        search_kwargs = {"flags": re.IGNORECASE}
+        search_flags = re.IGNORECASE
 
     if matching_model.matching_algorithm == MatchingModel.MATCH_NONE:
         return False
 
     elif matching_model.matching_algorithm == MatchingModel.MATCH_ALL:
         for word in _split_match(matching_model):
-            search_result = re.search(rf"\b{word}\b", document_content, **search_kwargs)
+            search_result = re.search(
+                rf"\b{word}\b",
+                document_content,
+                flags=search_flags,
+            )
             if not search_result:
                 return False
         log_reason(
@@ -177,7 +199,7 @@ def matches(matching_model: MatchingModel, document: Document):
 
     elif matching_model.matching_algorithm == MatchingModel.MATCH_ANY:
         for word in _split_match(matching_model):
-            if re.search(rf"\b{word}\b", document_content, **search_kwargs):
+            if re.search(rf"\b{word}\b", document_content, flags=search_flags):
                 log_reason(matching_model, document, f"it contains this word: {word}")
                 return True
         return False
@@ -187,7 +209,7 @@ def matches(matching_model: MatchingModel, document: Document):
             re.search(
                 rf"\b{re.escape(matching_model.match)}\b",
                 document_content,
-                **search_kwargs,
+                flags=search_flags,
             ),
         )
         if result:
@@ -199,16 +221,11 @@ def matches(matching_model: MatchingModel, document: Document):
         return result
 
     elif matching_model.matching_algorithm == MatchingModel.MATCH_REGEX:
-        try:
-            match = re.search(
-                re.compile(matching_model.match, **search_kwargs),
-                document_content,
-            )
-        except re.error:
-            logger.error(
-                f"Error while processing regular expression {matching_model.match}",
-            )
-            return False
+        match = safe_regex_search(
+            matching_model.match,
+            document_content,
+            flags=search_flags,
+        )
         if match:
             log_reason(
                 matching_model,
@@ -314,11 +331,19 @@ def consumable_document_matches_workflow(
         trigger_matched = False
 
     # Document path vs trigger path
+
+    # Use the original_path if set, else us the original_file
+    match_against = (
+        document.original_path
+        if document.original_path is not None
+        else document.original_file
+    )
+
     if (
         trigger.filter_path is not None
         and len(trigger.filter_path) > 0
         and not fnmatch(
-            document.original_file,
+            match_against,
             trigger.filter_path,
         )
     ):
@@ -334,67 +359,181 @@ def consumable_document_matches_workflow(
 def existing_document_matches_workflow(
     document: Document,
     trigger: WorkflowTrigger,
-) -> tuple[bool, str]:
+) -> tuple[bool, str | None]:
     """
     Returns True if the Document matches all filters from the workflow trigger,
     False otherwise. Includes a reason if doesn't match
     """
 
-    trigger_matched = True
-    reason = ""
-
+    # Check content matching algorithm
     if trigger.matching_algorithm > MatchingModel.MATCH_NONE and not matches(
         trigger,
         document,
     ):
-        reason = (
+        return (
+            False,
             f"Document content matching settings for algorithm '{trigger.matching_algorithm}' did not match",
         )
-        trigger_matched = False
 
-    # Document tags vs trigger has_tags
+    # Check if any tag filters exist to determine if we need to load document tags
+    trigger_has_tags_qs = trigger.filter_has_tags.all()
+    trigger_has_all_tags_qs = trigger.filter_has_all_tags.all()
+    trigger_has_not_tags_qs = trigger.filter_has_not_tags.all()
+
+    has_tags_filter = trigger_has_tags_qs.exists()
+    has_all_tags_filter = trigger_has_all_tags_qs.exists()
+    has_not_tags_filter = trigger_has_not_tags_qs.exists()
+
+    # Load document tags once if any tag filters exist
+    document_tag_ids = None
+    if has_tags_filter or has_all_tags_filter or has_not_tags_filter:
+        document_tag_ids = set(document.tags.values_list("id", flat=True))
+
+    # Document tags vs trigger has_tags (any of)
+    if has_tags_filter:
+        trigger_has_tag_ids = set(trigger_has_tags_qs.values_list("id", flat=True))
+        if not (document_tag_ids & trigger_has_tag_ids):
+            # For error message, load the actual tag objects
+            return (
+                False,
+                f"Document tags {list(document.tags.all())} do not include {list(trigger_has_tags_qs)}",
+            )
+
+    # Document tags vs trigger has_all_tags (all of)
+    if has_all_tags_filter:
+        required_tag_ids = set(trigger_has_all_tags_qs.values_list("id", flat=True))
+        if not required_tag_ids.issubset(document_tag_ids):
+            return (
+                False,
+                f"Document tags {list(document.tags.all())} do not contain all of {list(trigger_has_all_tags_qs)}",
+            )
+
+    # Document tags vs trigger has_not_tags (none of)
+    if has_not_tags_filter:
+        excluded_tag_ids = set(trigger_has_not_tags_qs.values_list("id", flat=True))
+        if document_tag_ids & excluded_tag_ids:
+            return (
+                False,
+                f"Document tags {list(document.tags.all())} include excluded tags {list(trigger_has_not_tags_qs)}",
+            )
+
+    allowed_correspondent_ids = set(
+        trigger.filter_has_any_correspondents.values_list("id", flat=True),
+    )
     if (
-        trigger.filter_has_tags.all().count() > 0
-        and document.tags.filter(
-            id__in=trigger.filter_has_tags.all().values_list("id"),
-        ).count()
-        == 0
+        allowed_correspondent_ids
+        and document.correspondent_id not in allowed_correspondent_ids
     ):
-        reason = (
-            f"Document tags {document.tags.all()} do not include"
-            f" {trigger.filter_has_tags.all()}",
+        return (
+            False,
+            f"Document correspondent {document.correspondent} is not one of {list(trigger.filter_has_any_correspondents.all())}",
         )
-        trigger_matched = False
 
     # Document correspondent vs trigger has_correspondent
     if (
-        trigger.filter_has_correspondent is not None
-        and document.correspondent != trigger.filter_has_correspondent
+        trigger.filter_has_correspondent_id is not None
+        and document.correspondent_id != trigger.filter_has_correspondent_id
     ):
-        reason = (
+        return (
+            False,
             f"Document correspondent {document.correspondent} does not match {trigger.filter_has_correspondent}",
         )
-        trigger_matched = False
+
+    if (
+        document.correspondent_id
+        and trigger.filter_has_not_correspondents.filter(
+            id=document.correspondent_id,
+        ).exists()
+    ):
+        return (
+            False,
+            f"Document correspondent {document.correspondent} is excluded by {list(trigger.filter_has_not_correspondents.all())}",
+        )
+
+    allowed_document_type_ids = set(
+        trigger.filter_has_any_document_types.values_list("id", flat=True),
+    )
+    if allowed_document_type_ids and (
+        document.document_type_id not in allowed_document_type_ids
+    ):
+        return (
+            False,
+            f"Document doc type {document.document_type} is not one of {list(trigger.filter_has_any_document_types.all())}",
+        )
 
     # Document document_type vs trigger has_document_type
     if (
-        trigger.filter_has_document_type is not None
-        and document.document_type != trigger.filter_has_document_type
+        trigger.filter_has_document_type_id is not None
+        and document.document_type_id != trigger.filter_has_document_type_id
     ):
-        reason = (
+        return (
+            False,
             f"Document doc type {document.document_type} does not match {trigger.filter_has_document_type}",
         )
-        trigger_matched = False
+
+    if (
+        document.document_type_id
+        and trigger.filter_has_not_document_types.filter(
+            id=document.document_type_id,
+        ).exists()
+    ):
+        return (
+            False,
+            f"Document doc type {document.document_type} is excluded by {list(trigger.filter_has_not_document_types.all())}",
+        )
+
+    allowed_storage_path_ids = set(
+        trigger.filter_has_any_storage_paths.values_list("id", flat=True),
+    )
+    if allowed_storage_path_ids and (
+        document.storage_path_id not in allowed_storage_path_ids
+    ):
+        return (
+            False,
+            f"Document storage path {document.storage_path} is not one of {list(trigger.filter_has_any_storage_paths.all())}",
+        )
 
     # Document storage_path vs trigger has_storage_path
     if (
-        trigger.filter_has_storage_path is not None
-        and document.storage_path != trigger.filter_has_storage_path
+        trigger.filter_has_storage_path_id is not None
+        and document.storage_path_id != trigger.filter_has_storage_path_id
     ):
-        reason = (
+        return (
+            False,
             f"Document storage path {document.storage_path} does not match {trigger.filter_has_storage_path}",
         )
-        trigger_matched = False
+
+    if (
+        document.storage_path_id
+        and trigger.filter_has_not_storage_paths.filter(
+            id=document.storage_path_id,
+        ).exists()
+    ):
+        return (
+            False,
+            f"Document storage path {document.storage_path} is excluded by {list(trigger.filter_has_not_storage_paths.all())}",
+        )
+
+    # Custom field query check
+    if trigger.filter_custom_field_query:
+        parser = CustomFieldQueryParser("filter_custom_field_query")
+        try:
+            custom_field_q, annotations = parser.parse(
+                trigger.filter_custom_field_query,
+            )
+        except serializers.ValidationError:
+            return (False, "Invalid custom field query configuration")
+
+        qs = (
+            Document.objects.filter(id=document.id)
+            .annotate(**annotations)
+            .filter(custom_field_q)
+        )
+        if not qs.exists():
+            return (
+                False,
+                "Document custom fields do not match the configured custom field query",
+            )
 
     # Document original_filename vs trigger filename
     if (
@@ -406,13 +545,12 @@ def existing_document_matches_workflow(
             trigger.filter_filename.lower(),
         )
     ):
-        reason = (
-            f"Document filename {document.original_filename} does not match"
-            f" {trigger.filter_filename.lower()}",
+        return (
+            False,
+            f"Document filename {document.original_filename} does not match {trigger.filter_filename.lower()}",
         )
-        trigger_matched = False
 
-    return (trigger_matched, reason)
+    return (True, None)
 
 
 def prefilter_documents_by_workflowtrigger(
@@ -425,31 +563,78 @@ def prefilter_documents_by_workflowtrigger(
     document_matches_workflow in run_workflows
     """
 
-    if trigger.filter_has_tags.all().count() > 0:
-        documents = documents.filter(
-            tags__in=trigger.filter_has_tags.all(),
-        ).distinct()
+    # Filter for documents that have AT LEAST ONE of the specified tags.
+    if trigger.filter_has_tags.exists():
+        documents = documents.filter(tags__in=trigger.filter_has_tags.all()).distinct()
 
+    # Filter for documents that have ALL of the specified tags.
+    if trigger.filter_has_all_tags.exists():
+        for tag in trigger.filter_has_all_tags.all():
+            documents = documents.filter(tags=tag)
+        # Multiple JOINs can create duplicate results.
+        documents = documents.distinct()
+
+    # Exclude documents that have ANY of the specified tags.
+    if trigger.filter_has_not_tags.exists():
+        documents = documents.exclude(tags__in=trigger.filter_has_not_tags.all())
+
+    # Correspondent, DocumentType, etc. filtering
+
+    if trigger.filter_has_any_correspondents.exists():
+        documents = documents.filter(
+            correspondent__in=trigger.filter_has_any_correspondents.all(),
+        )
     if trigger.filter_has_correspondent is not None:
         documents = documents.filter(
             correspondent=trigger.filter_has_correspondent,
         )
+    if trigger.filter_has_not_correspondents.exists():
+        documents = documents.exclude(
+            correspondent__in=trigger.filter_has_not_correspondents.all(),
+        )
 
+    if trigger.filter_has_any_document_types.exists():
+        documents = documents.filter(
+            document_type__in=trigger.filter_has_any_document_types.all(),
+        )
     if trigger.filter_has_document_type is not None:
         documents = documents.filter(
             document_type=trigger.filter_has_document_type,
         )
+    if trigger.filter_has_not_document_types.exists():
+        documents = documents.exclude(
+            document_type__in=trigger.filter_has_not_document_types.all(),
+        )
 
+    if trigger.filter_has_any_storage_paths.exists():
+        documents = documents.filter(
+            storage_path__in=trigger.filter_has_any_storage_paths.all(),
+        )
     if trigger.filter_has_storage_path is not None:
         documents = documents.filter(
             storage_path=trigger.filter_has_storage_path,
         )
+    if trigger.filter_has_not_storage_paths.exists():
+        documents = documents.exclude(
+            storage_path__in=trigger.filter_has_not_storage_paths.all(),
+        )
 
-    if trigger.filter_filename is not None and len(trigger.filter_filename) > 0:
-        # the true fnmatch will actually run later so we just want a loose filter here
+    # Custom Field & Filename Filtering
+
+    if trigger.filter_custom_field_query:
+        parser = CustomFieldQueryParser("filter_custom_field_query")
+        try:
+            custom_field_q, annotations = parser.parse(
+                trigger.filter_custom_field_query,
+            )
+        except serializers.ValidationError:
+            return documents.none()
+
+        documents = documents.annotate(**annotations).filter(custom_field_q)
+
+    if trigger.filter_filename:
         regex = fnmatch_translate(trigger.filter_filename).lstrip("^").rstrip("$")
-        regex = f"(?i){regex}"
-        documents = documents.filter(original_filename__regex=regex)
+        documents = documents.filter(original_filename__iregex=regex)
 
     return documents
 
@@ -464,13 +649,37 @@ def document_matches_workflow(
     settings from the workflow trigger, False otherwise
     """
 
+    triggers_queryset = (
+        workflow.triggers.filter(
+            type=trigger_type,
+        )
+        .select_related(
+            "filter_mailrule",
+            "filter_has_document_type",
+            "filter_has_correspondent",
+            "filter_has_storage_path",
+            "schedule_date_custom_field",
+        )
+        .prefetch_related(
+            "filter_has_tags",
+            "filter_has_all_tags",
+            "filter_has_not_tags",
+            "filter_has_any_document_types",
+            "filter_has_not_document_types",
+            "filter_has_any_correspondents",
+            "filter_has_not_correspondents",
+            "filter_has_any_storage_paths",
+            "filter_has_not_storage_paths",
+        )
+    )
+
     trigger_matched = True
-    if workflow.triggers.filter(type=trigger_type).count() == 0:
+    if not triggers_queryset.exists():
         trigger_matched = False
         logger.info(f"Document did not match {workflow}")
         logger.debug(f"No matching triggers with type {trigger_type} found")
     else:
-        for trigger in workflow.triggers.filter(type=trigger_type):
+        for trigger in triggers_queryset:
             if trigger_type == WorkflowTrigger.WorkflowTriggerType.CONSUMPTION:
                 trigger_matched, reason = consumable_document_matches_workflow(
                     document,

src/documents/migrations/0002_auto_20151226_1316.py

@@ -1,26 +0,0 @@
-# Generated by Django 1.9 on 2015-12-26 13:16
-
-import django.utils.timezone
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0001_initial"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="document",
-            options={"ordering": ("sender", "title")},
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="created",
-            field=models.DateTimeField(
-                default=django.utils.timezone.now,
-                editable=False,
-            ),
-        ),
-    ]

src/documents/migrations/0002_initial.py

@@ -1,50 +1,49 @@
-# Generated by Django 4.1.5 on 2023-03-04 22:33
+# Generated by Django 5.2.9 on 2026-01-20 18:46
 
+import django.db.models.deletion
 from django.db import migrations
 from django.db import models
 
 
 class Migration(migrations.Migration):
+    initial = True
+
     dependencies = [
-        ("documents", "1032_alter_correspondent_matching_algorithm_and_more"),
+        ("documents", "0001_initial"),
+        ("paperless_mail", "0001_initial"),
     ]
 
     operations = [
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "document type",
-                "verbose_name_plural": "document types",
-            },
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="filter_mailrule",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                to="paperless_mail.mailrule",
+                verbose_name="filter documents from this mail rule",
+            ),
         ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "tag",
-                "verbose_name_plural": "tags",
-            },
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="schedule_date_custom_field",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                to="documents.customfield",
+                verbose_name="schedule date custom field",
+            ),
         ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="storagepath",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
+        migrations.AddField(
+            model_name="workflow",
+            name="triggers",
+            field=models.ManyToManyField(
+                related_name="workflows",
+                to="documents.workflowtrigger",
+                verbose_name="triggers",
+            ),
         ),
         migrations.AddConstraint(
             model_name="correspondent",
@@ -61,6 +60,13 @@ class Migration(migrations.Migration):
                 name="documents_correspondent_name_uniq",
             ),
         ),
+        migrations.AddConstraint(
+            model_name="customfieldinstance",
+            constraint=models.UniqueConstraint(
+                fields=("document", "field"),
+                name="documents_customfieldinstance_unique_document_field",
+            ),
+        ),
         migrations.AddConstraint(
             model_name="documenttype",
             constraint=models.UniqueConstraint(

src/documents/migrations/0003_sender.py

@@ -1,70 +0,0 @@
-# Generated by Django 1.9 on 2016-01-11 12:21
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-from django.template.defaultfilters import slugify
-
-DOCUMENT_SENDER_MAP = {}
-
-
-def move_sender_strings_to_sender_model(apps, schema_editor):
-    sender_model = apps.get_model("documents", "Sender")
-    document_model = apps.get_model("documents", "Document")
-
-    # Create the sender and log the relationship with the document
-    for document in document_model.objects.all():
-        if document.sender:
-            (
-                DOCUMENT_SENDER_MAP[document.pk],
-                _,
-            ) = sender_model.objects.get_or_create(
-                name=document.sender,
-                defaults={"slug": slugify(document.sender)},
-            )
-
-
-def realign_senders(apps, schema_editor):
-    document_model = apps.get_model("documents", "Document")
-    for pk, sender in DOCUMENT_SENDER_MAP.items():
-        document_model.objects.filter(pk=pk).update(sender=sender)
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0002_auto_20151226_1316"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="Sender",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, unique=True)),
-                ("slug", models.SlugField()),
-            ],
-        ),
-        migrations.RunPython(move_sender_strings_to_sender_model),
-        migrations.RemoveField(
-            model_name="document",
-            name="sender",
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="sender",
-            field=models.ForeignKey(
-                blank=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                to="documents.Sender",
-            ),
-        ),
-        migrations.RunPython(realign_senders),
-    ]

src/documents/migrations/0003_workflowaction_order.py

@@ -0,0 +1,18 @@
+# Generated by Django 5.2.9 on 2026-01-20 20:06
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0002_initial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowaction",
+            name="order",
+            field=models.PositiveIntegerField(default=0, verbose_name="order"),
+        ),
+    ]

src/documents/migrations/0004_auto_20160114_1844.py

@@ -1,25 +0,0 @@
-# Generated by Django 1.9 on 2016-01-14 18:44
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0003_sender"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="sender",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="documents",
-                to="documents.Sender",
-            ),
-        ),
-    ]

src/documents/migrations/0004_auto_20160114_1844_squashed_0011_auto_20160303_1929.py

@@ -1,178 +0,0 @@
-# Generated by Django 4.2.13 on 2024-06-28 17:52
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    replaces = [
-        ("documents", "0004_auto_20160114_1844"),
-        ("documents", "0005_auto_20160123_0313"),
-        ("documents", "0006_auto_20160123_0430"),
-        ("documents", "0007_auto_20160126_2114"),
-        ("documents", "0008_document_file_type"),
-        ("documents", "0009_auto_20160214_0040"),
-        ("documents", "0010_log"),
-        ("documents", "0011_auto_20160303_1929"),
-    ]
-
-    dependencies = [
-        ("documents", "0003_sender"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="sender",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="documents",
-                to="documents.sender",
-            ),
-        ),
-        migrations.AlterModelOptions(
-            name="sender",
-            options={"ordering": ("name",)},
-        ),
-        migrations.CreateModel(
-            name="Tag",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, unique=True)),
-                ("slug", models.SlugField(blank=True)),
-                (
-                    "colour",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "#a6cee3"),
-                            (2, "#1f78b4"),
-                            (3, "#b2df8a"),
-                            (4, "#33a02c"),
-                            (5, "#fb9a99"),
-                            (6, "#e31a1c"),
-                            (7, "#fdbf6f"),
-                            (8, "#ff7f00"),
-                            (9, "#cab2d6"),
-                            (10, "#6a3d9a"),
-                            (11, "#b15928"),
-                            (12, "#000000"),
-                            (13, "#cccccc"),
-                        ],
-                        default=1,
-                    ),
-                ),
-                ("match", models.CharField(blank=True, max_length=256)),
-                (
-                    "matching_algorithm",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "Any"),
-                            (2, "All"),
-                            (3, "Literal"),
-                            (4, "Regular Expression"),
-                        ],
-                        default=1,
-                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
-                    ),
-                ),
-            ],
-            options={
-                "abstract": False,
-            },
-        ),
-        migrations.AlterField(
-            model_name="sender",
-            name="slug",
-            field=models.SlugField(blank=True),
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="file_type",
-            field=models.CharField(
-                choices=[
-                    ("pdf", "PDF"),
-                    ("png", "PNG"),
-                    ("jpg", "JPG"),
-                    ("gif", "GIF"),
-                    ("tiff", "TIFF"),
-                ],
-                default="pdf",
-                editable=False,
-                max_length=4,
-            ),
-            preserve_default=False,
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="tags",
-            field=models.ManyToManyField(
-                blank=True,
-                related_name="documents",
-                to="documents.tag",
-            ),
-        ),
-        migrations.CreateModel(
-            name="Log",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("group", models.UUIDField(blank=True)),
-                ("message", models.TextField()),
-                (
-                    "level",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (10, "Debugging"),
-                            (20, "Informational"),
-                            (30, "Warning"),
-                            (40, "Error"),
-                            (50, "Critical"),
-                        ],
-                        default=20,
-                    ),
-                ),
-                (
-                    "component",
-                    models.PositiveIntegerField(
-                        choices=[(1, "Consumer"), (2, "Mail Fetcher")],
-                    ),
-                ),
-                ("created", models.DateTimeField(auto_now_add=True)),
-                ("modified", models.DateTimeField(auto_now=True)),
-            ],
-            options={
-                "ordering": ("-modified",),
-            },
-        ),
-        migrations.RenameModel(
-            old_name="Sender",
-            new_name="Correspondent",
-        ),
-        migrations.AlterModelOptions(
-            name="document",
-            options={"ordering": ("correspondent", "title")},
-        ),
-        migrations.RenameField(
-            model_name="document",
-            old_name="sender",
-            new_name="correspondent",
-        ),
-    ]

src/documents/migrations/0004_remove_document_storage_type.py

@@ -0,0 +1,16 @@
+# Generated by Django 5.2.9 on 2026-01-24 23:05
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0003_workflowaction_order"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="document",
+            name="storage_type",
+        ),
+    ]

src/documents/migrations/0005_auto_20160123_0313.py

@@ -1,16 +0,0 @@
-# Generated by Django 1.9 on 2016-01-23 03:13
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0004_auto_20160114_1844"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="sender",
-            options={"ordering": ("name",)},
-        ),
-    ]

src/documents/migrations/0005_workflowtrigger_filter_has_any_correspondents_and_more.py

@@ -0,0 +1,43 @@
+# Generated by Django 5.2.7 on 2025-12-17 22:25
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0004_remove_document_storage_type"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="filter_has_any_correspondents",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="workflowtriggers_has_any_correspondent",
+                to="documents.correspondent",
+                verbose_name="has one of these correspondents",
+            ),
+        ),
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="filter_has_any_document_types",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="workflowtriggers_has_any_document_type",
+                to="documents.documenttype",
+                verbose_name="has one of these document types",
+            ),
+        ),
+        migrations.AddField(
+            model_name="workflowtrigger",
+            name="filter_has_any_storage_paths",
+            field=models.ManyToManyField(
+                blank=True,
+                related_name="workflowtriggers_has_any_storage_path",
+                to="documents.storagepath",
+                verbose_name="has one of these storage paths",
+            ),
+        ),
+    ]

src/documents/migrations/0006_alter_document_checksum_unique.py

@@ -0,0 +1,23 @@
+# Generated by Django 5.2.7 on 2026-01-14 17:45
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0005_workflowtrigger_filter_has_any_correspondents_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="checksum",
+            field=models.CharField(
+                editable=False,
+                max_length=32,
+                verbose_name="checksum",
+                help_text="The checksum of the original document.",
+            ),
+        ),
+    ]

src/documents/migrations/0006_auto_20160123_0430.py

@@ -1,64 +0,0 @@
-# Generated by Django 1.9 on 2016-01-23 04:30
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0005_auto_20160123_0313"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="Tag",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, unique=True)),
-                ("slug", models.SlugField(blank=True)),
-                (
-                    "colour",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "#a6cee3"),
-                            (2, "#1f78b4"),
-                            (3, "#b2df8a"),
-                            (4, "#33a02c"),
-                            (5, "#fb9a99"),
-                            (6, "#e31a1c"),
-                            (7, "#fdbf6f"),
-                            (8, "#ff7f00"),
-                            (9, "#cab2d6"),
-                            (10, "#6a3d9a"),
-                            (11, "#ffff99"),
-                            (12, "#b15928"),
-                            (13, "#000000"),
-                            (14, "#cccccc"),
-                        ],
-                        default=1,
-                    ),
-                ),
-            ],
-            options={
-                "abstract": False,
-            },
-        ),
-        migrations.AlterField(
-            model_name="sender",
-            name="slug",
-            field=models.SlugField(blank=True),
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="tags",
-            field=models.ManyToManyField(related_name="documents", to="documents.Tag"),
-        ),
-    ]

src/documents/migrations/0007_auto_20160126_2114.py

@@ -1,55 +0,0 @@
-# Generated by Django 1.9 on 2016-01-26 21:14
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0006_auto_20160123_0430"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="tag",
-            name="match",
-            field=models.CharField(blank=True, max_length=256),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                blank=True,
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                ],
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
-                null=True,
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="colour",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "#a6cee3"),
-                    (2, "#1f78b4"),
-                    (3, "#b2df8a"),
-                    (4, "#33a02c"),
-                    (5, "#fb9a99"),
-                    (6, "#e31a1c"),
-                    (7, "#fdbf6f"),
-                    (8, "#ff7f00"),
-                    (9, "#cab2d6"),
-                    (10, "#6a3d9a"),
-                    (11, "#b15928"),
-                    (12, "#000000"),
-                    (13, "#cccccc"),
-                ],
-                default=1,
-            ),
-        ),
-    ]

src/documents/migrations/0007_document_content_length.py

@@ -0,0 +1,25 @@
+# Generated by Django 5.2.6 on 2026-01-24 07:33
+
+import django.db.models.functions.text
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0006_alter_document_checksum_unique"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="document",
+            name="content_length",
+            field=models.GeneratedField(
+                db_persist=True,
+                expression=django.db.models.functions.text.Length("content"),
+                null=False,
+                help_text="Length of the content field in characters. Automatically maintained by the database for faster statistics computation.",
+                output_field=models.PositiveIntegerField(default=0),
+            ),
+        ),
+    ]

src/documents/migrations/0008_document_file_type.py

@@ -1,39 +0,0 @@
-# Generated by Django 1.9 on 2016-01-29 22:58
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0007_auto_20160126_2114"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="file_type",
-            field=models.CharField(
-                choices=[
-                    ("pdf", "PDF"),
-                    ("png", "PNG"),
-                    ("jpg", "JPG"),
-                    ("gif", "GIF"),
-                    ("tiff", "TIFF"),
-                ],
-                default="pdf",
-                editable=False,
-                max_length=4,
-            ),
-            preserve_default=False,
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="tags",
-            field=models.ManyToManyField(
-                blank=True,
-                related_name="documents",
-                to="documents.Tag",
-            ),
-        ),
-    ]

src/documents/migrations/0008_sharelinkbundle.py

@@ -0,0 +1,177 @@
+# Generated by Django 5.2.9 on 2026-01-27 01:09
+
+import django.db.models.deletion
+import django.db.models.functions.text
+import django.utils.timezone
+from django.conf import settings
+from django.contrib.auth.management import create_permissions
+from django.contrib.auth.models import Group
+from django.contrib.auth.models import Permission
+from django.contrib.auth.models import User
+from django.db import migrations
+from django.db import models
+
+
+def grant_share_link_bundle_permissions(apps, schema_editor):
+    # Ensure newly introduced permissions are created for all apps
+    for app_config in apps.get_app_configs():
+        app_config.models_module = True
+        create_permissions(app_config, apps=apps, verbosity=0)
+        app_config.models_module = None
+
+    add_document_perm = Permission.objects.filter(codename="add_document").first()
+    share_bundle_permissions = Permission.objects.filter(
+        codename__contains="sharelinkbundle",
+    )
+
+    users = User.objects.filter(user_permissions=add_document_perm).distinct()
+    for user in users:
+        user.user_permissions.add(*share_bundle_permissions)
+
+    groups = Group.objects.filter(permissions=add_document_perm).distinct()
+    for group in groups:
+        group.permissions.add(*share_bundle_permissions)
+
+
+def revoke_share_link_bundle_permissions(apps, schema_editor):
+    share_bundle_permissions = Permission.objects.filter(
+        codename__contains="sharelinkbundle",
+    )
+    for user in User.objects.all():
+        user.user_permissions.remove(*share_bundle_permissions)
+    for group in Group.objects.all():
+        group.permissions.remove(*share_bundle_permissions)
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+        ("documents", "0007_document_content_length"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ShareLinkBundle",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    models.DateTimeField(
+                        blank=True,
+                        db_index=True,
+                        default=django.utils.timezone.now,
+                        editable=False,
+                        verbose_name="created",
+                    ),
+                ),
+                (
+                    "expiration",
+                    models.DateTimeField(
+                        blank=True,
+                        db_index=True,
+                        null=True,
+                        verbose_name="expiration",
+                    ),
+                ),
+                (
+                    "slug",
+                    models.SlugField(
+                        blank=True,
+                        editable=False,
+                        unique=True,
+                        verbose_name="slug",
+                    ),
+                ),
+                (
+                    "file_version",
+                    models.CharField(
+                        choices=[("archive", "Archive"), ("original", "Original")],
+                        default="archive",
+                        max_length=50,
+                    ),
+                ),
+                (
+                    "status",
+                    models.CharField(
+                        choices=[
+                            ("pending", "Pending"),
+                            ("processing", "Processing"),
+                            ("ready", "Ready"),
+                            ("failed", "Failed"),
+                        ],
+                        default="pending",
+                        max_length=50,
+                    ),
+                ),
+                (
+                    "size_bytes",
+                    models.PositiveIntegerField(
+                        blank=True,
+                        null=True,
+                        verbose_name="size (bytes)",
+                    ),
+                ),
+                (
+                    "last_error",
+                    models.JSONField(
+                        blank=True,
+                        null=True,
+                        default=None,
+                        verbose_name="last error",
+                    ),
+                ),
+                (
+                    "file_path",
+                    models.CharField(
+                        blank=True,
+                        max_length=512,
+                        verbose_name="file path",
+                    ),
+                ),
+                (
+                    "built_at",
+                    models.DateTimeField(
+                        blank=True,
+                        null=True,
+                        verbose_name="built at",
+                    ),
+                ),
+                (
+                    "documents",
+                    models.ManyToManyField(
+                        related_name="share_link_bundles",
+                        to="documents.document",
+                        verbose_name="documents",
+                    ),
+                ),
+                (
+                    "owner",
+                    models.ForeignKey(
+                        blank=True,
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        related_name="share_link_bundles",
+                        to=settings.AUTH_USER_MODEL,
+                        verbose_name="owner",
+                    ),
+                ),
+            ],
+            options={
+                "ordering": ("-created",),
+                "verbose_name": "share link bundle",
+                "verbose_name_plural": "share link bundles",
+            },
+        ),
+        migrations.RunPython(
+            grant_share_link_bundle_permissions,
+            reverse_code=revoke_share_link_bundle_permissions,
+        ),
+    ]

src/documents/migrations/0009_auto_20160214_0040.py

@@ -1,27 +0,0 @@
-# Generated by Django 1.9 on 2016-02-14 00:40
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0008_document_file_type"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
-            ),
-        ),
-    ]

src/documents/migrations/0009_workflowaction_passwords_alter_workflowaction_type.py

@@ -0,0 +1,38 @@
+# Generated by Django 5.2.7 on 2025-12-29 03:56
+
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0008_sharelinkbundle"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="workflowaction",
+            name="passwords",
+            field=models.JSONField(
+                blank=True,
+                help_text="Passwords to try when removing PDF protection. Separate with commas or new lines.",
+                null=True,
+                verbose_name="passwords",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="workflowaction",
+            name="type",
+            field=models.PositiveIntegerField(
+                choices=[
+                    (1, "Assignment"),
+                    (2, "Removal"),
+                    (3, "Email"),
+                    (4, "Webhook"),
+                    (5, "Password removal"),
+                ],
+                default=1,
+                verbose_name="Workflow Action Type",
+            ),
+        ),
+    ]

src/documents/migrations/0010_alter_document_content_length.py

@@ -0,0 +1,25 @@
+# Generated by Django 5.2.11 on 2026-02-07 19:06
+
+import django.db.models.functions.text
+from django.db import migrations
+from django.db import models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("documents", "0009_workflowaction_passwords_alter_workflowaction_type"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="document",
+            name="content_length",
+            field=models.GeneratedField(
+                db_persist=True,
+                expression=django.db.models.functions.text.Length("content"),
+                help_text="Length of the content field in characters. Automatically maintained by the database for faster statistics computation.",
+                output_field=models.PositiveIntegerField(default=0),
+                serialize=False,
+            ),
+        ),
+    ]

src/documents/migrations/0010_log.py

@@ -1,53 +0,0 @@
-# Generated by Django 1.9 on 2016-02-27 17:54
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0009_auto_20160214_0040"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="Log",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("group", models.UUIDField(blank=True)),
-                ("message", models.TextField()),
-                (
-                    "level",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (10, "Debugging"),
-                            (20, "Informational"),
-                            (30, "Warning"),
-                            (40, "Error"),
-                            (50, "Critical"),
-                        ],
-                        default=20,
-                    ),
-                ),
-                (
-                    "component",
-                    models.PositiveIntegerField(
-                        choices=[(1, "Consumer"), (2, "Mail Fetcher")],
-                    ),
-                ),
-                ("created", models.DateTimeField(auto_now_add=True)),
-                ("modified", models.DateTimeField(auto_now=True)),
-            ],
-            options={
-                "ordering": ("-modified",),
-            },
-        ),
-    ]

src/documents/migrations/0011_auto_20160303_1929.py

@@ -1,26 +0,0 @@
-# Generated by Django 1.9.2 on 2016-03-03 19:29
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    atomic = False
-    dependencies = [
-        ("documents", "0010_log"),
-    ]
-
-    operations = [
-        migrations.RenameModel(
-            old_name="Sender",
-            new_name="Correspondent",
-        ),
-        migrations.AlterModelOptions(
-            name="document",
-            options={"ordering": ("correspondent", "title")},
-        ),
-        migrations.RenameField(
-            model_name="document",
-            old_name="sender",
-            new_name="correspondent",
-        ),
-    ]

src/documents/migrations/0012_auto_20160305_0040.py

@@ -1,128 +0,0 @@
-# Generated by Django 1.9.2 on 2016-03-05 00:40
-
-import os
-import re
-import shutil
-import subprocess
-import tempfile
-from pathlib import Path
-
-import gnupg
-from django.conf import settings
-from django.db import migrations
-from django.utils.termcolors import colorize as colourise  # Spelling hurts me
-
-
-class GnuPG:
-    """
-    A handy singleton to use when handling encrypted files.
-    """
-
-    gpg = gnupg.GPG(gnupghome=settings.GNUPG_HOME)
-
-    @classmethod
-    def decrypted(cls, file_handle):
-        return cls.gpg.decrypt_file(file_handle, passphrase=settings.PASSPHRASE).data
-
-    @classmethod
-    def encrypted(cls, file_handle):
-        return cls.gpg.encrypt_file(
-            file_handle,
-            recipients=None,
-            passphrase=settings.PASSPHRASE,
-            symmetric=True,
-        ).data
-
-
-def move_documents_and_create_thumbnails(apps, schema_editor):
-    (Path(settings.MEDIA_ROOT) / "documents" / "originals").mkdir(
-        parents=True,
-        exist_ok=True,
-    )
-    (Path(settings.MEDIA_ROOT) / "documents" / "thumbnails").mkdir(
-        parents=True,
-        exist_ok=True,
-    )
-
-    documents: list[str] = os.listdir(Path(settings.MEDIA_ROOT) / "documents")  # noqa: PTH208
-
-    if set(documents) == {"originals", "thumbnails"}:
-        return
-
-    print(
-        colourise(
-            "\n\n"
-            "  This is a one-time only migration to generate thumbnails for all of your\n"
-            "  documents so that future UIs will have something to work with.  If you have\n"
-            "  a lot of documents though, this may take a while, so a coffee break may be\n"
-            "  in order."
-            "\n",
-            opts=("bold",),
-        ),
-    )
-
-    Path(settings.SCRATCH_DIR).mkdir(parents=True, exist_ok=True)
-
-    for f in sorted(documents):
-        if not f.endswith("gpg"):
-            continue
-
-        print(
-            "    {} {} {}".format(
-                colourise("*", fg="green"),
-                colourise("Generating a thumbnail for", fg="white"),
-                colourise(f, fg="cyan"),
-            ),
-        )
-
-        thumb_temp: str = tempfile.mkdtemp(prefix="paperless", dir=settings.SCRATCH_DIR)
-        orig_temp: str = tempfile.mkdtemp(prefix="paperless", dir=settings.SCRATCH_DIR)
-
-        orig_source: Path = Path(settings.MEDIA_ROOT) / "documents" / f
-        orig_target: Path = Path(orig_temp) / f.replace(".gpg", "")
-
-        with orig_source.open("rb") as encrypted, orig_target.open("wb") as unencrypted:
-            unencrypted.write(GnuPG.decrypted(encrypted))
-
-        subprocess.Popen(
-            (
-                settings.CONVERT_BINARY,
-                "-scale",
-                "500x5000",
-                "-alpha",
-                "remove",
-                orig_target,
-                Path(thumb_temp) / "convert-%04d.png",
-            ),
-        ).wait()
-
-        thumb_source: Path = Path(thumb_temp) / "convert-0000.png"
-        thumb_target: Path = (
-            Path(settings.MEDIA_ROOT)
-            / "documents"
-            / "thumbnails"
-            / re.sub(r"(\d+)\.\w+(\.gpg)", "\\1.png\\2", f)
-        )
-        with (
-            thumb_source.open("rb") as unencrypted,
-            thumb_target.open("wb") as encrypted,
-        ):
-            encrypted.write(GnuPG.encrypted(unencrypted))
-
-        shutil.rmtree(thumb_temp)
-        shutil.rmtree(orig_temp)
-
-        shutil.move(
-            Path(settings.MEDIA_ROOT) / "documents" / f,
-            Path(settings.MEDIA_ROOT) / "documents" / "originals" / f,
-        )
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0011_auto_20160303_1929"),
-    ]
-
-    operations = [
-        migrations.RunPython(move_documents_and_create_thumbnails),
-    ]

src/documents/migrations/0013_auto_20160325_2111.py

@@ -1,42 +0,0 @@
-# Generated by Django 1.9.4 on 2016-03-25 21:11
-
-import django.utils.timezone
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0012_auto_20160305_0040"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="correspondent",
-            name="match",
-            field=models.CharField(blank=True, max_length=256),
-        ),
-        migrations.AddField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  If you don\'t know what a regex is, you probably don\'t want this option.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="created",
-            field=models.DateTimeField(default=django.utils.timezone.now),
-        ),
-        migrations.RemoveField(
-            model_name="log",
-            name="component",
-        ),
-    ]

src/documents/migrations/0014_document_checksum.py

@@ -1,182 +0,0 @@
-# Generated by Django 1.9.4 on 2016-03-28 19:09
-
-import hashlib
-from pathlib import Path
-
-import django.utils.timezone
-import gnupg
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-from django.template.defaultfilters import slugify
-from django.utils.termcolors import colorize as colourise  # Spelling hurts me
-
-
-class GnuPG:
-    """
-    A handy singleton to use when handling encrypted files.
-    """
-
-    gpg = gnupg.GPG(gnupghome=settings.GNUPG_HOME)
-
-    @classmethod
-    def decrypted(cls, file_handle):
-        return cls.gpg.decrypt_file(file_handle, passphrase=settings.PASSPHRASE).data
-
-    @classmethod
-    def encrypted(cls, file_handle):
-        return cls.gpg.encrypt_file(
-            file_handle,
-            recipients=None,
-            passphrase=settings.PASSPHRASE,
-            symmetric=True,
-        ).data
-
-
-class Document:
-    """
-    Django's migrations restrict access to model methods, so this is a snapshot
-    of the methods that existed at the time this migration was written, since
-    we need to make use of a lot of these shortcuts here.
-    """
-
-    def __init__(self, doc):
-        self.pk = doc.pk
-        self.correspondent = doc.correspondent
-        self.title = doc.title
-        self.file_type = doc.file_type
-        self.tags = doc.tags
-        self.created = doc.created
-
-    def __str__(self):
-        created = self.created.strftime("%Y%m%d%H%M%S")
-        if self.correspondent and self.title:
-            return f"{created}: {self.correspondent} - {self.title}"
-        if self.correspondent or self.title:
-            return f"{created}: {self.correspondent or self.title}"
-        return str(created)
-
-    @property
-    def source_path(self):
-        return (
-            Path(settings.MEDIA_ROOT)
-            / "documents"
-            / "originals"
-            / f"{self.pk:07}.{self.file_type}.gpg"
-        )
-
-    @property
-    def source_file(self):
-        return self.source_path.open("rb")
-
-    @property
-    def file_name(self):
-        return slugify(str(self)) + "." + self.file_type
-
-
-def set_checksums(apps, schema_editor):
-    document_model = apps.get_model("documents", "Document")
-
-    if not document_model.objects.all().exists():
-        return
-
-    print(
-        colourise(
-            "\n\n"
-            "  This is a one-time only migration to generate checksums for all\n"
-            "  of your existing documents.  If you have a lot of documents\n"
-            "  though, this may take a while, so a coffee break may be in\n"
-            "  order."
-            "\n",
-            opts=("bold",),
-        ),
-    )
-
-    sums = {}
-    for d in document_model.objects.all():
-        document = Document(d)
-
-        print(
-            "    {} {} {}".format(
-                colourise("*", fg="green"),
-                colourise("Generating a checksum for", fg="white"),
-                colourise(document.file_name, fg="cyan"),
-            ),
-        )
-
-        with document.source_file as encrypted:
-            checksum = hashlib.md5(GnuPG.decrypted(encrypted)).hexdigest()
-
-        if checksum in sums:
-            error = "\n{line}{p1}\n\n{doc1}\n{doc2}\n\n{p2}\n\n{code}\n\n{p3}{line}".format(
-                p1=colourise(
-                    "It appears that you have two identical documents in your collection and \nPaperless no longer supports this (see issue #97).  The documents in question\nare:",
-                    fg="yellow",
-                ),
-                p2=colourise(
-                    "To fix this problem, you'll have to remove one of them from the database, a task\nmost easily done by running the following command in the same\ndirectory as manage.py:",
-                    fg="yellow",
-                ),
-                p3=colourise(
-                    "When that's finished, re-run the migrate, and provided that there aren't any\nother duplicates, you should be good to go.",
-                    fg="yellow",
-                ),
-                doc1=colourise(
-                    f"  * {sums[checksum][1]} (id: {sums[checksum][0]})",
-                    fg="red",
-                ),
-                doc2=colourise(
-                    f"  * {document.file_name} (id: {document.pk})",
-                    fg="red",
-                ),
-                code=colourise(
-                    f"  $ echo 'DELETE FROM documents_document WHERE id = {document.pk};' | ./manage.py dbshell",
-                    fg="green",
-                ),
-                line=colourise("\n{}\n".format("=" * 80), fg="white", opts=("bold",)),
-            )
-            raise RuntimeError(error)
-        sums[checksum] = (document.pk, document.file_name)
-
-        document_model.objects.filter(pk=document.pk).update(checksum=checksum)
-
-
-def do_nothing(apps, schema_editor):
-    pass
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0013_auto_20160325_2111"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                default="-",
-                db_index=True,
-                editable=False,
-                max_length=32,
-                help_text="The checksum of the original document (before it "
-                "was encrypted).  We use this to prevent duplicate "
-                "document imports.",
-            ),
-            preserve_default=False,
-        ),
-        migrations.RunPython(set_checksums, do_nothing),
-        migrations.AlterField(
-            model_name="document",
-            name="created",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="modified",
-            field=models.DateTimeField(auto_now=True, db_index=True),
-        ),
-    ]

src/documents/migrations/0015_add_insensitive_to_match.py

@@ -1,33 +0,0 @@
-# Generated by Django 1.10.2 on 2016-10-05 21:38
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0014_document_checksum"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                help_text="The checksum of the original document (before it was encrypted).  We use this to prevent duplicate document imports.",
-                max_length=32,
-                unique=True,
-            ),
-        ),
-        migrations.AddField(
-            model_name="correspondent",
-            name="is_insensitive",
-            field=models.BooleanField(default=True),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="is_insensitive",
-            field=models.BooleanField(default=True),
-        ),
-    ]

src/documents/migrations/0015_add_insensitive_to_match_squashed_0018_auto_20170715_1712.py

@@ -1,92 +0,0 @@
-# Generated by Django 4.2.13 on 2024-06-28 17:57
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    replaces = [
-        ("documents", "0015_add_insensitive_to_match"),
-        ("documents", "0016_auto_20170325_1558"),
-        ("documents", "0017_auto_20170512_0507"),
-        ("documents", "0018_auto_20170715_1712"),
-    ]
-
-    dependencies = [
-        ("documents", "0014_document_checksum"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                help_text="The checksum of the original document (before it was encrypted).  We use this to prevent duplicate document imports.",
-                max_length=32,
-                unique=True,
-            ),
-        ),
-        migrations.AddField(
-            model_name="correspondent",
-            name="is_insensitive",
-            field=models.BooleanField(default=True),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="is_insensitive",
-            field=models.BooleanField(default=True),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="content",
-            field=models.TextField(
-                blank=True,
-                db_index=("mysql" not in settings.DATABASES["default"]["ENGINE"]),
-                help_text="The raw, text-only data of the document.  This field is primarily used for searching.",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="correspondent",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.correspondent",
-            ),
-        ),
-    ]

src/documents/migrations/0016_auto_20170325_1558.py

@@ -1,23 +0,0 @@
-# Generated by Django 1.10.5 on 2017-03-25 15:58
-
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0015_add_insensitive_to_match"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="content",
-            field=models.TextField(
-                blank=True,
-                db_index=("mysql" not in settings.DATABASES["default"]["ENGINE"]),
-                help_text="The raw, text-only data of the document.  This field is primarily used for searching.",
-            ),
-        ),
-    ]

src/documents/migrations/0017_auto_20170512_0507.py

@@ -1,43 +0,0 @@
-# Generated by Django 1.10.5 on 2017-05-12 05:07
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0016_auto_20170325_1558"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-    ]

src/documents/migrations/0018_auto_20170715_1712.py

@@ -1,25 +0,0 @@
-# Generated by Django 1.10.5 on 2017-07-15 17:12
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0017_auto_20170512_0507"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="correspondent",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.Correspondent",
-            ),
-        ),
-    ]

src/documents/migrations/0019_add_consumer_user.py

@@ -1,22 +0,0 @@
-# Generated by Django 1.10.5 on 2017-07-15 17:12
-
-from django.contrib.auth.models import User
-from django.db import migrations
-
-
-def forwards_func(apps, schema_editor):
-    User.objects.create(username="consumer")
-
-
-def reverse_func(apps, schema_editor):
-    User.objects.get(username="consumer").delete()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0018_auto_20170715_1712"),
-    ]
-
-    operations = [
-        migrations.RunPython(forwards_func, reverse_func),
-    ]

src/documents/migrations/0020_document_added.py

@@ -1,29 +0,0 @@
-import django.utils.timezone
-from django.db import migrations
-from django.db import models
-
-
-def set_added_time_to_created_time(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-    for doc in Document.objects.all():
-        doc.added = doc.created
-        doc.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0019_add_consumer_user"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="added",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-                editable=False,
-            ),
-        ),
-        migrations.RunPython(set_added_time_to_created_time),
-    ]

src/documents/migrations/0021_document_storage_type.py

@@ -1,41 +0,0 @@
-# Generated by Django 1.11.10 on 2018-02-04 13:07
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0020_document_added"),
-    ]
-
-    operations = [
-        # Add the field with the default GPG-encrypted value
-        migrations.AddField(
-            model_name="document",
-            name="storage_type",
-            field=models.CharField(
-                choices=[
-                    ("unencrypted", "Unencrypted"),
-                    ("gpg", "Encrypted with GNU Privacy Guard"),
-                ],
-                default="gpg",
-                editable=False,
-                max_length=11,
-            ),
-        ),
-        # Now that the field is added, change the default to unencrypted
-        migrations.AlterField(
-            model_name="document",
-            name="storage_type",
-            field=models.CharField(
-                choices=[
-                    ("unencrypted", "Unencrypted"),
-                    ("gpg", "Encrypted with GNU Privacy Guard"),
-                ],
-                default="unencrypted",
-                editable=False,
-                max_length=11,
-            ),
-        ),
-    ]

src/documents/migrations/0022_auto_20181007_1420.py

@@ -1,61 +0,0 @@
-# Generated by Django 2.0.8 on 2018-10-07 14:20
-
-from django.db import migrations
-from django.db import models
-from django.utils.text import slugify
-
-
-def re_slug_all_the_things(apps, schema_editor):
-    """
-    Rewrite all slug values to make sure they're actually slugs before we brand
-    them as uneditable.
-    """
-
-    Tag = apps.get_model("documents", "Tag")
-    Correspondent = apps.get_model("documents", "Correspondent")
-
-    for klass in (Tag, Correspondent):
-        for instance in klass.objects.all():
-            klass.objects.filter(pk=instance.pk).update(slug=slugify(instance.slug))
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0021_document_storage_type"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="tag",
-            options={"ordering": ("name",)},
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="slug",
-            field=models.SlugField(blank=True, editable=False),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="file_type",
-            field=models.CharField(
-                choices=[
-                    ("pdf", "PDF"),
-                    ("png", "PNG"),
-                    ("jpg", "JPG"),
-                    ("gif", "GIF"),
-                    ("tiff", "TIFF"),
-                    ("txt", "TXT"),
-                    ("csv", "CSV"),
-                    ("md", "MD"),
-                ],
-                editable=False,
-                max_length=4,
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="slug",
-            field=models.SlugField(blank=True, editable=False),
-        ),
-        migrations.RunPython(re_slug_all_the_things, migrations.RunPython.noop),
-    ]

src/documents/migrations/0023_document_current_filename.py

@@ -1,39 +0,0 @@
-# Generated by Django 2.0.10 on 2019-04-26 18:57
-
-from django.db import migrations
-from django.db import models
-
-
-def set_filename(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-    for doc in Document.objects.all():
-        file_name = f"{doc.pk:07}.{doc.file_type}"
-        if doc.storage_type == "gpg":
-            file_name += ".gpg"
-
-        # Set filename
-        doc.filename = file_name
-
-        # Save document
-        doc.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0022_auto_20181007_1420"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="filename",
-            field=models.FilePathField(
-                default=None,
-                null=True,
-                editable=False,
-                help_text="Current filename in storage",
-                max_length=256,
-            ),
-        ),
-        migrations.RunPython(set_filename),
-    ]

src/documents/migrations/1000_update_paperless_all.py

@@ -1,147 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-07 12:35
-import uuid
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-def logs_set_default_group(apps, schema_editor):
-    Log = apps.get_model("documents", "Log")
-    for log in Log.objects.all():
-        if log.group is None:
-            log.group = uuid.uuid4()
-            log.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "0023_document_current_filename"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="archive_serial_number",
-            field=models.IntegerField(
-                blank=True,
-                db_index=True,
-                help_text="The position of this document in your physical document archive.",
-                null=True,
-                unique=True,
-            ),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="is_inbox_tag",
-            field=models.BooleanField(
-                default=False,
-                help_text="Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.",
-            ),
-        ),
-        migrations.CreateModel(
-            name="DocumentType",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, unique=True)),
-                ("slug", models.SlugField(blank=True, editable=False)),
-                ("match", models.CharField(blank=True, max_length=256)),
-                (
-                    "matching_algorithm",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "Any"),
-                            (2, "All"),
-                            (3, "Literal"),
-                            (4, "Regular Expression"),
-                            (5, "Fuzzy Match"),
-                            (6, "Automatic Classification"),
-                        ],
-                        default=1,
-                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-                    ),
-                ),
-                ("is_insensitive", models.BooleanField(default=True)),
-            ],
-            options={
-                "abstract": False,
-                "ordering": ("name",),
-            },
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="document_type",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.documenttype",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                    (6, "Automatic Classification"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any"),
-                    (2, "All"),
-                    (3, "Literal"),
-                    (4, "Regular Expression"),
-                    (5, "Fuzzy Match"),
-                    (6, "Automatic Classification"),
-                ],
-                default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="content",
-            field=models.TextField(
-                blank=True,
-                help_text="The raw, text-only data of the document. This field is primarily used for searching.",
-            ),
-        ),
-        migrations.AlterModelOptions(
-            name="log",
-            options={"ordering": ("-created",)},
-        ),
-        migrations.RemoveField(
-            model_name="log",
-            name="modified",
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="group",
-            field=models.UUIDField(blank=True, null=True),
-        ),
-        migrations.RunPython(
-            code=django.db.migrations.operations.special.RunPython.noop,
-            reverse_code=logs_set_default_group,
-        ),
-    ]

src/documents/migrations/1001_auto_20201109_1636.py

@@ -1,13 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-09 16:36
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1000_update_paperless_all"),
-    ]
-
-    operations = [
-        migrations.RunPython(migrations.RunPython.noop, migrations.RunPython.noop),
-    ]

src/documents/migrations/1002_auto_20201111_1105.py

@@ -1,24 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-11 11:05
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1001_auto_20201109_1636"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="filename",
-            field=models.FilePathField(
-                default=None,
-                editable=False,
-                help_text="Current filename in storage",
-                max_length=1024,
-                null=True,
-            ),
-        ),
-    ]

src/documents/migrations/1003_mime_types.py

@@ -1,92 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-20 11:21
-from pathlib import Path
-
-import magic
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-from paperless.db import GnuPG
-
-STORAGE_TYPE_UNENCRYPTED = "unencrypted"
-STORAGE_TYPE_GPG = "gpg"
-
-
-def source_path(self) -> Path:
-    if self.filename:
-        fname: str = str(self.filename)
-    else:
-        fname = f"{self.pk:07}.{self.file_type}"
-        if self.storage_type == STORAGE_TYPE_GPG:
-            fname += ".gpg"
-
-    return Path(settings.ORIGINALS_DIR) / fname
-
-
-def add_mime_types(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-    documents = Document.objects.all()
-
-    for d in documents:
-        with Path(source_path(d)).open("rb") as f:
-            if d.storage_type == STORAGE_TYPE_GPG:
-                data = GnuPG.decrypted(f)
-            else:
-                data = f.read(1024)
-
-        d.mime_type = magic.from_buffer(data, mime=True)
-        d.save()
-
-
-def add_file_extensions(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-    documents = Document.objects.all()
-
-    for d in documents:
-        d.file_type = Path(d.filename).suffix.lstrip(".")
-        d.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1002_auto_20201111_1105"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="mime_type",
-            field=models.CharField(default="-", editable=False, max_length=256),
-            preserve_default=False,
-        ),
-        migrations.RunPython(add_mime_types, migrations.RunPython.noop),
-        # This operation is here so that we can revert the entire migration:
-        # By allowing this field to be blank and null, we can revert the
-        # remove operation further down and the database won't complain about
-        # NOT NULL violations.
-        migrations.AlterField(
-            model_name="document",
-            name="file_type",
-            field=models.CharField(
-                choices=[
-                    ("pdf", "PDF"),
-                    ("png", "PNG"),
-                    ("jpg", "JPG"),
-                    ("gif", "GIF"),
-                    ("tiff", "TIFF"),
-                    ("txt", "TXT"),
-                    ("csv", "CSV"),
-                    ("md", "MD"),
-                ],
-                editable=False,
-                max_length=4,
-                null=True,
-                blank=True,
-            ),
-        ),
-        migrations.RunPython(migrations.RunPython.noop, add_file_extensions),
-        migrations.RemoveField(
-            model_name="document",
-            name="file_type",
-        ),
-    ]

src/documents/migrations/1004_sanity_check_schedule.py

@@ -1,12 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-25 14:53
-
-from django.db import migrations
-from django.db.migrations import RunPython
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1003_mime_types"),
-    ]
-
-    operations = [RunPython(migrations.RunPython.noop, migrations.RunPython.noop)]

src/documents/migrations/1005_checksums.py

@@ -1,34 +0,0 @@
-# Generated by Django 3.1.3 on 2020-11-29 00:48
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1004_sanity_check_schedule"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="archive_checksum",
-            field=models.CharField(
-                blank=True,
-                editable=False,
-                help_text="The checksum of the archived document.",
-                max_length=32,
-                null=True,
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                help_text="The checksum of the original document.",
-                max_length=32,
-                unique=True,
-            ),
-        ),
-    ]

src/documents/migrations/1006_auto_20201208_2209.py

@@ -1,24 +0,0 @@
-# Generated by Django 3.1.4 on 2020-12-08 22:09
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1005_checksums"),
-    ]
-
-    operations = [
-        migrations.RemoveField(
-            model_name="correspondent",
-            name="slug",
-        ),
-        migrations.RemoveField(
-            model_name="documenttype",
-            name="slug",
-        ),
-        migrations.RemoveField(
-            model_name="tag",
-            name="slug",
-        ),
-    ]

src/documents/migrations/1006_auto_20201208_2209_squashed_1011_auto_20210101_2340.py

@@ -1,485 +0,0 @@
-# Generated by Django 4.2.13 on 2024-06-28 18:01
-
-import django.db.models.deletion
-import django.utils.timezone
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    replaces = [
-        ("documents", "1006_auto_20201208_2209"),
-        ("documents", "1007_savedview_savedviewfilterrule"),
-        ("documents", "1008_auto_20201216_1736"),
-        ("documents", "1009_auto_20201216_2005"),
-        ("documents", "1010_auto_20210101_2159"),
-        ("documents", "1011_auto_20210101_2340"),
-    ]
-
-    dependencies = [
-        ("documents", "1005_checksums"),
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-    ]
-
-    operations = [
-        migrations.RemoveField(
-            model_name="correspondent",
-            name="slug",
-        ),
-        migrations.RemoveField(
-            model_name="documenttype",
-            name="slug",
-        ),
-        migrations.RemoveField(
-            model_name="tag",
-            name="slug",
-        ),
-        migrations.CreateModel(
-            name="SavedView",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128, verbose_name="name")),
-                (
-                    "show_on_dashboard",
-                    models.BooleanField(verbose_name="show on dashboard"),
-                ),
-                (
-                    "show_in_sidebar",
-                    models.BooleanField(verbose_name="show in sidebar"),
-                ),
-                (
-                    "sort_field",
-                    models.CharField(max_length=128, verbose_name="sort field"),
-                ),
-                (
-                    "sort_reverse",
-                    models.BooleanField(default=False, verbose_name="sort reverse"),
-                ),
-                (
-                    "user",
-                    models.ForeignKey(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        to=settings.AUTH_USER_MODEL,
-                        verbose_name="user",
-                    ),
-                ),
-            ],
-            options={
-                "ordering": ("name",),
-                "verbose_name": "saved view",
-                "verbose_name_plural": "saved views",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="correspondent",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "correspondent",
-                "verbose_name_plural": "correspondents",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="document",
-            options={
-                "ordering": ("-created",),
-                "verbose_name": "document",
-                "verbose_name_plural": "documents",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={
-                "verbose_name": "document type",
-                "verbose_name_plural": "document types",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="log",
-            options={
-                "ordering": ("-created",),
-                "verbose_name": "log",
-                "verbose_name_plural": "logs",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={"verbose_name": "tag", "verbose_name_plural": "tags"},
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="added",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-                editable=False,
-                verbose_name="added",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="archive_checksum",
-            field=models.CharField(
-                blank=True,
-                editable=False,
-                help_text="The checksum of the archived document.",
-                max_length=32,
-                null=True,
-                verbose_name="archive checksum",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="archive_serial_number",
-            field=models.IntegerField(
-                blank=True,
-                db_index=True,
-                help_text="The position of this document in your physical document archive.",
-                null=True,
-                unique=True,
-                verbose_name="archive serial number",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                help_text="The checksum of the original document.",
-                max_length=32,
-                unique=True,
-                verbose_name="checksum",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="content",
-            field=models.TextField(
-                blank=True,
-                help_text="The raw, text-only data of the document. This field is primarily used for searching.",
-                verbose_name="content",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="correspondent",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.correspondent",
-                verbose_name="correspondent",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="created",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-                verbose_name="created",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="document_type",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.documenttype",
-                verbose_name="document type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="filename",
-            field=models.FilePathField(
-                default=None,
-                editable=False,
-                help_text="Current filename in storage",
-                max_length=1024,
-                null=True,
-                verbose_name="filename",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="mime_type",
-            field=models.CharField(
-                editable=False,
-                max_length=256,
-                verbose_name="mime type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="modified",
-            field=models.DateTimeField(
-                auto_now=True,
-                db_index=True,
-                verbose_name="modified",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="storage_type",
-            field=models.CharField(
-                choices=[
-                    ("unencrypted", "Unencrypted"),
-                    ("gpg", "Encrypted with GNU Privacy Guard"),
-                ],
-                default="unencrypted",
-                editable=False,
-                max_length=11,
-                verbose_name="storage type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="tags",
-            field=models.ManyToManyField(
-                blank=True,
-                related_name="documents",
-                to="documents.tag",
-                verbose_name="tags",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="title",
-            field=models.CharField(
-                blank=True,
-                db_index=True,
-                max_length=128,
-                verbose_name="title",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="created",
-            field=models.DateTimeField(auto_now_add=True, verbose_name="created"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="group",
-            field=models.UUIDField(blank=True, null=True, verbose_name="group"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="level",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (10, "debug"),
-                    (20, "information"),
-                    (30, "warning"),
-                    (40, "error"),
-                    (50, "critical"),
-                ],
-                default=20,
-                verbose_name="level",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="message",
-            field=models.TextField(verbose_name="message"),
-        ),
-        migrations.CreateModel(
-            name="SavedViewFilterRule",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "rule_type",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (0, "title contains"),
-                            (1, "content contains"),
-                            (2, "ASN is"),
-                            (3, "correspondent is"),
-                            (4, "document type is"),
-                            (5, "is in inbox"),
-                            (6, "has tag"),
-                            (7, "has any tag"),
-                            (8, "created before"),
-                            (9, "created after"),
-                            (10, "created year is"),
-                            (11, "created month is"),
-                            (12, "created day is"),
-                            (13, "added before"),
-                            (14, "added after"),
-                            (15, "modified before"),
-                            (16, "modified after"),
-                            (17, "does not have tag"),
-                        ],
-                        verbose_name="rule type",
-                    ),
-                ),
-                (
-                    "value",
-                    models.CharField(
-                        blank=True,
-                        max_length=128,
-                        null=True,
-                        verbose_name="value",
-                    ),
-                ),
-                (
-                    "saved_view",
-                    models.ForeignKey(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="filter_rules",
-                        to="documents.savedview",
-                        verbose_name="saved view",
-                    ),
-                ),
-            ],
-            options={
-                "verbose_name": "filter rule",
-                "verbose_name_plural": "filter rules",
-            },
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="colour",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "#a6cee3"),
-                    (2, "#1f78b4"),
-                    (3, "#b2df8a"),
-                    (4, "#33a02c"),
-                    (5, "#fb9a99"),
-                    (6, "#e31a1c"),
-                    (7, "#fdbf6f"),
-                    (8, "#ff7f00"),
-                    (9, "#cab2d6"),
-                    (10, "#6a3d9a"),
-                    (11, "#b15928"),
-                    (12, "#000000"),
-                    (13, "#cccccc"),
-                ],
-                default=1,
-                verbose_name="color",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="is_inbox_tag",
-            field=models.BooleanField(
-                default=False,
-                help_text="Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.",
-                verbose_name="is inbox tag",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-    ]

src/documents/migrations/1007_savedview_savedviewfilterrule.py

@@ -1,90 +0,0 @@
-# Generated by Django 3.1.4 on 2020-12-12 14:41
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1006_auto_20201208_2209"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="SavedView",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("name", models.CharField(max_length=128)),
-                ("show_on_dashboard", models.BooleanField()),
-                ("show_in_sidebar", models.BooleanField()),
-                ("sort_field", models.CharField(max_length=128)),
-                ("sort_reverse", models.BooleanField(default=False)),
-                (
-                    "user",
-                    models.ForeignKey(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        to=settings.AUTH_USER_MODEL,
-                    ),
-                ),
-            ],
-        ),
-        migrations.CreateModel(
-            name="SavedViewFilterRule",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "rule_type",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (0, "Title contains"),
-                            (1, "Content contains"),
-                            (2, "ASN is"),
-                            (3, "Correspondent is"),
-                            (4, "Document type is"),
-                            (5, "Is in inbox"),
-                            (6, "Has tag"),
-                            (7, "Has any tag"),
-                            (8, "Created before"),
-                            (9, "Created after"),
-                            (10, "Created year is"),
-                            (11, "Created month is"),
-                            (12, "Created day is"),
-                            (13, "Added before"),
-                            (14, "Added after"),
-                            (15, "Modified before"),
-                            (16, "Modified after"),
-                            (17, "Does not have tag"),
-                        ],
-                    ),
-                ),
-                ("value", models.CharField(max_length=128)),
-                (
-                    "saved_view",
-                    models.ForeignKey(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="filter_rules",
-                        to="documents.savedview",
-                    ),
-                ),
-            ],
-        ),
-    ]

src/documents/migrations/1008_auto_20201216_1736.py

@@ -1,33 +0,0 @@
-# Generated by Django 3.1.4 on 2020-12-16 17:36
-
-import django.db.models.functions.text
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1007_savedview_savedviewfilterrule"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="correspondent",
-            options={"ordering": (django.db.models.functions.text.Lower("name"),)},
-        ),
-        migrations.AlterModelOptions(
-            name="document",
-            options={"ordering": ("-created",)},
-        ),
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={"ordering": (django.db.models.functions.text.Lower("name"),)},
-        ),
-        migrations.AlterModelOptions(
-            name="savedview",
-            options={"ordering": (django.db.models.functions.text.Lower("name"),)},
-        ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={"ordering": (django.db.models.functions.text.Lower("name"),)},
-        ),
-    ]

src/documents/migrations/1009_auto_20201216_2005.py

@@ -1,28 +0,0 @@
-# Generated by Django 3.1.4 on 2020-12-16 20:05
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1008_auto_20201216_1736"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="correspondent",
-            options={"ordering": ("name",)},
-        ),
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={"ordering": ("name",)},
-        ),
-        migrations.AlterModelOptions(
-            name="savedview",
-            options={"ordering": ("name",)},
-        ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={"ordering": ("name",)},
-        ),
-    ]

src/documents/migrations/1010_auto_20210101_2159.py

@@ -1,18 +0,0 @@
-# Generated by Django 3.1.4 on 2021-01-01 21:59
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1009_auto_20201216_2005"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="value",
-            field=models.CharField(blank=True, max_length=128, null=True),
-        ),
-    ]

src/documents/migrations/1011_auto_20210101_2340.py

@@ -1,454 +0,0 @@
-# Generated by Django 3.1.4 on 2021-01-01 23:40
-
-import django.db.models.deletion
-import django.utils.timezone
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1010_auto_20210101_2159"),
-    ]
-
-    operations = [
-        migrations.AlterModelOptions(
-            name="correspondent",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "correspondent",
-                "verbose_name_plural": "correspondents",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="document",
-            options={
-                "ordering": ("-created",),
-                "verbose_name": "document",
-                "verbose_name_plural": "documents",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={
-                "verbose_name": "document type",
-                "verbose_name_plural": "document types",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="log",
-            options={
-                "ordering": ("-created",),
-                "verbose_name": "log",
-                "verbose_name_plural": "logs",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="savedview",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "saved view",
-                "verbose_name_plural": "saved views",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="savedviewfilterrule",
-            options={
-                "verbose_name": "filter rule",
-                "verbose_name_plural": "filter rules",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={"verbose_name": "tag", "verbose_name_plural": "tags"},
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="added",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-                editable=False,
-                verbose_name="added",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="archive_checksum",
-            field=models.CharField(
-                blank=True,
-                editable=False,
-                help_text="The checksum of the archived document.",
-                max_length=32,
-                null=True,
-                verbose_name="archive checksum",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="archive_serial_number",
-            field=models.IntegerField(
-                blank=True,
-                db_index=True,
-                help_text="The position of this document in your physical document archive.",
-                null=True,
-                unique=True,
-                verbose_name="archive serial number",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="checksum",
-            field=models.CharField(
-                editable=False,
-                help_text="The checksum of the original document.",
-                max_length=32,
-                unique=True,
-                verbose_name="checksum",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="content",
-            field=models.TextField(
-                blank=True,
-                help_text="The raw, text-only data of the document. This field is primarily used for searching.",
-                verbose_name="content",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="correspondent",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.correspondent",
-                verbose_name="correspondent",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="created",
-            field=models.DateTimeField(
-                db_index=True,
-                default=django.utils.timezone.now,
-                verbose_name="created",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="document_type",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.documenttype",
-                verbose_name="document type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="filename",
-            field=models.FilePathField(
-                default=None,
-                editable=False,
-                help_text="Current filename in storage",
-                max_length=1024,
-                null=True,
-                verbose_name="filename",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="mime_type",
-            field=models.CharField(
-                editable=False,
-                max_length=256,
-                verbose_name="mime type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="modified",
-            field=models.DateTimeField(
-                auto_now=True,
-                db_index=True,
-                verbose_name="modified",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="storage_type",
-            field=models.CharField(
-                choices=[
-                    ("unencrypted", "Unencrypted"),
-                    ("gpg", "Encrypted with GNU Privacy Guard"),
-                ],
-                default="unencrypted",
-                editable=False,
-                max_length=11,
-                verbose_name="storage type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="tags",
-            field=models.ManyToManyField(
-                blank=True,
-                related_name="documents",
-                to="documents.Tag",
-                verbose_name="tags",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="title",
-            field=models.CharField(
-                blank=True,
-                db_index=True,
-                max_length=128,
-                verbose_name="title",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="created",
-            field=models.DateTimeField(auto_now_add=True, verbose_name="created"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="group",
-            field=models.UUIDField(blank=True, null=True, verbose_name="group"),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="level",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (10, "debug"),
-                    (20, "information"),
-                    (30, "warning"),
-                    (40, "error"),
-                    (50, "critical"),
-                ],
-                default=20,
-                verbose_name="level",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="log",
-            name="message",
-            field=models.TextField(verbose_name="message"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="show_in_sidebar",
-            field=models.BooleanField(verbose_name="show in sidebar"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="show_on_dashboard",
-            field=models.BooleanField(verbose_name="show on dashboard"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="sort_field",
-            field=models.CharField(max_length=128, verbose_name="sort field"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="sort_reverse",
-            field=models.BooleanField(default=False, verbose_name="sort reverse"),
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="user",
-            field=models.ForeignKey(
-                on_delete=django.db.models.deletion.CASCADE,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="user",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="saved_view",
-            field=models.ForeignKey(
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="filter_rules",
-                to="documents.savedview",
-                verbose_name="saved view",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="value",
-            field=models.CharField(
-                blank=True,
-                max_length=128,
-                null=True,
-                verbose_name="value",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="colour",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "#a6cee3"),
-                    (2, "#1f78b4"),
-                    (3, "#b2df8a"),
-                    (4, "#33a02c"),
-                    (5, "#fb9a99"),
-                    (6, "#e31a1c"),
-                    (7, "#fdbf6f"),
-                    (8, "#ff7f00"),
-                    (9, "#cab2d6"),
-                    (10, "#6a3d9a"),
-                    (11, "#b15928"),
-                    (12, "#000000"),
-                    (13, "#cccccc"),
-                ],
-                default=1,
-                verbose_name="color",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="is_inbox_tag",
-            field=models.BooleanField(
-                default=False,
-                help_text="Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags.",
-                verbose_name="is inbox tag",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="is_insensitive",
-            field=models.BooleanField(default=True, verbose_name="is insensitive"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="match",
-            field=models.CharField(blank=True, max_length=256, verbose_name="match"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="name",
-            field=models.CharField(max_length=128, unique=True, verbose_name="name"),
-        ),
-    ]

src/documents/migrations/1012_fix_archive_files.py

@@ -1,367 +0,0 @@
-# Generated by Django 3.1.6 on 2021-02-07 22:26
-import datetime
-import hashlib
-import logging
-import os
-import shutil
-from collections import defaultdict
-from pathlib import Path
-from time import sleep
-
-import pathvalidate
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-from django.template.defaultfilters import slugify
-
-logger = logging.getLogger("paperless.migrations")
-
-
-###############################################################################
-# This is code copied straight paperless before the change.
-###############################################################################
-class defaultdictNoStr(defaultdict):
-    def __str__(self):  # pragma: no cover
-        raise ValueError("Don't use {tags} directly.")
-
-
-def many_to_dictionary(field):  # pragma: no cover
-    # Converts ManyToManyField to dictionary by assuming, that field
-    # entries contain an _ or - which will be used as a delimiter
-    mydictionary = dict()
-
-    for index, t in enumerate(field.all()):
-        # Populate tag names by index
-        mydictionary[index] = slugify(t.name)
-
-        # Find delimiter
-        delimiter = t.name.find("_")
-
-        if delimiter == -1:
-            delimiter = t.name.find("-")
-
-        if delimiter == -1:
-            continue
-
-        key = t.name[:delimiter]
-        value = t.name[delimiter + 1 :]
-
-        mydictionary[slugify(key)] = slugify(value)
-
-    return mydictionary
-
-
-def archive_name_from_filename(filename: Path) -> Path:
-    return Path(filename.stem + ".pdf")
-
-
-def archive_path_old(doc) -> Path:
-    if doc.filename:
-        fname = archive_name_from_filename(Path(doc.filename))
-    else:
-        fname = Path(f"{doc.pk:07}.pdf")
-
-    return settings.ARCHIVE_DIR / fname
-
-
-STORAGE_TYPE_GPG = "gpg"
-
-
-def archive_path_new(doc) -> Path | None:
-    if doc.archive_filename is not None:
-        return settings.ARCHIVE_DIR / doc.archive_filename
-    else:
-        return None
-
-
-def source_path(doc) -> Path:
-    if doc.filename:
-        fname = doc.filename
-    else:
-        fname = f"{doc.pk:07}{doc.file_type}"
-        if doc.storage_type == STORAGE_TYPE_GPG:
-            fname = Path(str(fname) + ".gpg")  # pragma: no cover
-
-    return settings.ORIGINALS_DIR / fname
-
-
-def generate_unique_filename(doc, *, archive_filename=False):
-    if archive_filename:
-        old_filename = doc.archive_filename
-        root = settings.ARCHIVE_DIR
-    else:
-        old_filename = doc.filename
-        root = settings.ORIGINALS_DIR
-
-    counter = 0
-
-    while True:
-        new_filename = generate_filename(
-            doc,
-            counter=counter,
-            archive_filename=archive_filename,
-        )
-        if new_filename == old_filename:
-            # still the same as before.
-            return new_filename
-
-        if (root / new_filename).exists():
-            counter += 1
-        else:
-            return new_filename
-
-
-def generate_filename(doc, *, counter=0, append_gpg=True, archive_filename=False):
-    path = ""
-
-    try:
-        if settings.FILENAME_FORMAT is not None:
-            tags = defaultdictNoStr(lambda: slugify(None), many_to_dictionary(doc.tags))
-
-            tag_list = pathvalidate.sanitize_filename(
-                ",".join(sorted([tag.name for tag in doc.tags.all()])),
-                replacement_text="-",
-            )
-
-            if doc.correspondent:
-                correspondent = pathvalidate.sanitize_filename(
-                    doc.correspondent.name,
-                    replacement_text="-",
-                )
-            else:
-                correspondent = "none"
-
-            if doc.document_type:
-                document_type = pathvalidate.sanitize_filename(
-                    doc.document_type.name,
-                    replacement_text="-",
-                )
-            else:
-                document_type = "none"
-
-            path = settings.FILENAME_FORMAT.format(
-                title=pathvalidate.sanitize_filename(doc.title, replacement_text="-"),
-                correspondent=correspondent,
-                document_type=document_type,
-                created=datetime.date.isoformat(doc.created),
-                created_year=doc.created.year if doc.created else "none",
-                created_month=f"{doc.created.month:02}" if doc.created else "none",
-                created_day=f"{doc.created.day:02}" if doc.created else "none",
-                added=datetime.date.isoformat(doc.added),
-                added_year=doc.added.year if doc.added else "none",
-                added_month=f"{doc.added.month:02}" if doc.added else "none",
-                added_day=f"{doc.added.day:02}" if doc.added else "none",
-                tags=tags,
-                tag_list=tag_list,
-            ).strip()
-
-            path = path.strip(os.sep)
-
-    except (ValueError, KeyError, IndexError):
-        logger.warning(
-            f"Invalid PAPERLESS_FILENAME_FORMAT: "
-            f"{settings.FILENAME_FORMAT}, falling back to default",
-        )
-
-    counter_str = f"_{counter:02}" if counter else ""
-
-    filetype_str = ".pdf" if archive_filename else doc.file_type
-
-    if len(path) > 0:
-        filename = f"{path}{counter_str}{filetype_str}"
-    else:
-        filename = f"{doc.pk:07}{counter_str}{filetype_str}"
-
-    # Append .gpg for encrypted files
-    if append_gpg and doc.storage_type == STORAGE_TYPE_GPG:
-        filename += ".gpg"
-
-    return filename
-
-
-###############################################################################
-# This code performs bidirection archive file transformation.
-###############################################################################
-
-
-def parse_wrapper(parser, path, mime_type, file_name):
-    # this is here so that I can mock this out for testing.
-    parser.parse(path, mime_type, file_name)
-
-
-def create_archive_version(doc, retry_count=3):
-    from documents.parsers import DocumentParser
-    from documents.parsers import ParseError
-    from documents.parsers import get_parser_class_for_mime_type
-
-    logger.info(f"Regenerating archive document for document ID:{doc.id}")
-    parser_class = get_parser_class_for_mime_type(doc.mime_type)
-    for try_num in range(retry_count):
-        parser: DocumentParser = parser_class(None, None)
-        try:
-            parse_wrapper(
-                parser,
-                source_path(doc),
-                doc.mime_type,
-                Path(doc.filename).name,
-            )
-            doc.content = parser.get_text()
-
-            if parser.get_archive_path() and Path(parser.get_archive_path()).is_file():
-                doc.archive_filename = generate_unique_filename(
-                    doc,
-                    archive_filename=True,
-                )
-                with Path(parser.get_archive_path()).open("rb") as f:
-                    doc.archive_checksum = hashlib.md5(f.read()).hexdigest()
-                archive_path_new(doc).parent.mkdir(parents=True, exist_ok=True)
-                shutil.copy2(parser.get_archive_path(), archive_path_new(doc))
-            else:
-                doc.archive_checksum = None
-                logger.error(
-                    f"Parser did not return an archive document for document "
-                    f"ID:{doc.id}. Removing archive document.",
-                )
-            doc.save()
-            return
-        except ParseError:
-            if try_num + 1 == retry_count:
-                logger.exception(
-                    f"Unable to regenerate archive document for ID:{doc.id}. You "
-                    f"need to invoke the document_archiver management command "
-                    f"manually for that document.",
-                )
-                doc.archive_checksum = None
-                doc.save()
-                return
-            else:
-                # This is mostly here for the tika parser in docker
-                # environments. The servers for parsing need to come up first,
-                # and the docker setup doesn't ensure that tika is running
-                # before attempting migrations.
-                logger.error("Parse error, will try again in 5 seconds...")
-                sleep(5)
-        finally:
-            parser.cleanup()
-
-
-def move_old_to_new_locations(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-
-    affected_document_ids = set()
-
-    old_archive_path_to_id = {}
-
-    # check for documents that have incorrect archive versions
-    for doc in Document.objects.filter(archive_checksum__isnull=False):
-        old_path = archive_path_old(doc)
-
-        if old_path in old_archive_path_to_id:
-            affected_document_ids.add(doc.id)
-            affected_document_ids.add(old_archive_path_to_id[old_path])
-        else:
-            old_archive_path_to_id[old_path] = doc.id
-
-    # check that archive files of all unaffected documents are in place
-    for doc in Document.objects.filter(archive_checksum__isnull=False):
-        old_path = archive_path_old(doc)
-        if doc.id not in affected_document_ids and not old_path.is_file():
-            raise ValueError(
-                f"Archived document ID:{doc.id} does not exist at: {old_path}",
-            )
-
-    # check that we can regenerate affected archive versions
-    for doc_id in affected_document_ids:
-        from documents.parsers import get_parser_class_for_mime_type
-
-        doc = Document.objects.get(id=doc_id)
-        parser_class = get_parser_class_for_mime_type(doc.mime_type)
-        if not parser_class:
-            raise ValueError(
-                f"Document ID:{doc.id} has an invalid archived document, "
-                f"but no parsers are available. Cannot migrate.",
-            )
-
-    for doc in Document.objects.filter(archive_checksum__isnull=False):
-        if doc.id in affected_document_ids:
-            old_path = archive_path_old(doc)
-            # remove affected archive versions
-            if old_path.is_file():
-                logger.debug(f"Removing {old_path}")
-                old_path.unlink()
-        else:
-            # Set archive path for unaffected files
-            doc.archive_filename = archive_name_from_filename(Path(doc.filename))
-            Document.objects.filter(id=doc.id).update(
-                archive_filename=doc.archive_filename,
-            )
-
-    # regenerate archive documents
-    for doc_id in affected_document_ids:
-        doc = Document.objects.get(id=doc_id)
-        create_archive_version(doc)
-
-
-def move_new_to_old_locations(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-
-    old_archive_paths = set()
-
-    for doc in Document.objects.filter(archive_checksum__isnull=False):
-        new_archive_path = archive_path_new(doc)
-        old_archive_path = archive_path_old(doc)
-        if old_archive_path in old_archive_paths:
-            raise ValueError(
-                f"Cannot migrate: Archive file name {old_archive_path} of "
-                f"document {doc.filename} would clash with another archive "
-                f"filename.",
-            )
-        old_archive_paths.add(old_archive_path)
-        if new_archive_path != old_archive_path and old_archive_path.is_file():
-            raise ValueError(
-                f"Cannot migrate: Cannot move {new_archive_path} to "
-                f"{old_archive_path}: file already exists.",
-            )
-
-    for doc in Document.objects.filter(archive_checksum__isnull=False):
-        new_archive_path = archive_path_new(doc)
-        old_archive_path = archive_path_old(doc)
-        if new_archive_path != old_archive_path:
-            logger.debug(f"Moving {new_archive_path} to {old_archive_path}")
-            shutil.move(new_archive_path, old_archive_path)
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1011_auto_20210101_2340"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="archive_filename",
-            field=models.FilePathField(
-                default=None,
-                editable=False,
-                help_text="Current archive filename in storage",
-                max_length=1024,
-                null=True,
-                unique=True,
-                verbose_name="archive filename",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="filename",
-            field=models.FilePathField(
-                default=None,
-                editable=False,
-                help_text="Current filename in storage",
-                max_length=1024,
-                null=True,
-                unique=True,
-                verbose_name="filename",
-            ),
-        ),
-        migrations.RunPython(move_old_to_new_locations, move_new_to_old_locations),
-    ]

src/documents/migrations/1013_migrate_tag_colour.py

@@ -1,74 +0,0 @@
-# Generated by Django 3.1.4 on 2020-12-02 21:43
-
-from django.db import migrations
-from django.db import models
-
-COLOURS_OLD = {
-    1: "#a6cee3",
-    2: "#1f78b4",
-    3: "#b2df8a",
-    4: "#33a02c",
-    5: "#fb9a99",
-    6: "#e31a1c",
-    7: "#fdbf6f",
-    8: "#ff7f00",
-    9: "#cab2d6",
-    10: "#6a3d9a",
-    11: "#b15928",
-    12: "#000000",
-    13: "#cccccc",
-}
-
-
-def forward(apps, schema_editor):
-    Tag = apps.get_model("documents", "Tag")
-
-    for tag in Tag.objects.all():
-        colour_old_id = tag.colour_old
-        rgb = COLOURS_OLD[colour_old_id]
-        tag.color = rgb
-        tag.save()
-
-
-def reverse(apps, schema_editor):
-    Tag = apps.get_model("documents", "Tag")
-
-    def _get_colour_id(rdb):
-        for idx, rdbx in COLOURS_OLD.items():
-            if rdbx == rdb:
-                return idx
-        # Return colour 1 if we can't match anything
-        return 1
-
-    for tag in Tag.objects.all():
-        colour_id = _get_colour_id(tag.color)
-        tag.colour_old = colour_id
-        tag.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1012_fix_archive_files"),
-    ]
-
-    operations = [
-        migrations.RenameField(
-            model_name="tag",
-            old_name="colour",
-            new_name="colour_old",
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="color",
-            field=models.CharField(
-                default="#a6cee3",
-                max_length=7,
-                verbose_name="color",
-            ),
-        ),
-        migrations.RunPython(forward, reverse),
-        migrations.RemoveField(
-            model_name="tag",
-            name="colour_old",
-        ),
-    ]

src/documents/migrations/1014_auto_20210228_1614.py

@@ -1,42 +0,0 @@
-# Generated by Django 3.1.7 on 2021-02-28 15:14
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1013_migrate_tag_colour"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1015_remove_null_characters.py

@@ -1,27 +0,0 @@
-# Generated by Django 3.1.7 on 2021-04-04 18:28
-import logging
-
-from django.db import migrations
-
-logger = logging.getLogger("paperless.migrations")
-
-
-def remove_null_characters(apps, schema_editor):
-    Document = apps.get_model("documents", "Document")
-
-    for doc in Document.objects.all():
-        content: str = doc.content
-        if "\0" in content:
-            logger.info(f"Removing null characters from document {doc}...")
-            doc.content = content.replace("\0", " ")
-            doc.save()
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1014_auto_20210228_1614"),
-    ]
-
-    operations = [
-        migrations.RunPython(remove_null_characters, migrations.RunPython.noop),
-    ]

src/documents/migrations/1016_auto_20210317_1351.py

@@ -1,54 +0,0 @@
-# Generated by Django 3.1.7 on 2021-03-17 12:51
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1015_remove_null_characters"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedview",
-            name="sort_field",
-            field=models.CharField(
-                blank=True,
-                max_length=128,
-                null=True,
-                verbose_name="sort field",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1016_auto_20210317_1351_squashed_1020_merge_20220518_1839.py

@@ -1,190 +0,0 @@
-# Generated by Django 4.2.13 on 2024-06-28 18:09
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    replaces = [
-        ("documents", "1016_auto_20210317_1351"),
-        ("documents", "1017_alter_savedviewfilterrule_rule_type"),
-        ("documents", "1018_alter_savedviewfilterrule_value"),
-        ("documents", "1019_uisettings"),
-        ("documents", "1019_storagepath_document_storage_path"),
-        ("documents", "1020_merge_20220518_1839"),
-    ]
-
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1015_remove_null_characters"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedview",
-            name="sort_field",
-            field=models.CharField(
-                blank=True,
-                max_length=128,
-                null=True,
-                verbose_name="sort field",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="value",
-            field=models.CharField(
-                blank=True,
-                max_length=255,
-                null=True,
-                verbose_name="value",
-            ),
-        ),
-        migrations.CreateModel(
-            name="UiSettings",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("settings", models.JSONField(null=True)),
-                (
-                    "user",
-                    models.OneToOneField(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="ui_settings",
-                        to=settings.AUTH_USER_MODEL,
-                    ),
-                ),
-            ],
-        ),
-        migrations.CreateModel(
-            name="StoragePath",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "name",
-                    models.CharField(max_length=128, unique=True, verbose_name="name"),
-                ),
-                (
-                    "match",
-                    models.CharField(blank=True, max_length=256, verbose_name="match"),
-                ),
-                (
-                    "matching_algorithm",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "Any word"),
-                            (2, "All words"),
-                            (3, "Exact match"),
-                            (4, "Regular expression"),
-                            (5, "Fuzzy word"),
-                            (6, "Automatic"),
-                        ],
-                        default=1,
-                        verbose_name="matching algorithm",
-                    ),
-                ),
-                (
-                    "is_insensitive",
-                    models.BooleanField(default=True, verbose_name="is insensitive"),
-                ),
-                ("path", models.CharField(max_length=512, verbose_name="path")),
-            ],
-            options={
-                "verbose_name": "storage path",
-                "verbose_name_plural": "storage paths",
-                "ordering": ("name",),
-            },
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="storage_path",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.storagepath",
-                verbose_name="storage path",
-            ),
-        ),
-    ]

src/documents/migrations/1017_alter_savedviewfilterrule_rule_type.py

@@ -1,45 +0,0 @@
-# Generated by Django 3.2.12 on 2022-03-17 11:59
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1016_auto_20210317_1351"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1018_alter_savedviewfilterrule_value.py

@@ -1,23 +0,0 @@
-# Generated by Django 4.0.3 on 2022-04-01 22:50
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1017_alter_savedviewfilterrule_rule_type"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="value",
-            field=models.CharField(
-                blank=True,
-                max_length=255,
-                null=True,
-                verbose_name="value",
-            ),
-        ),
-    ]

src/documents/migrations/1019_storagepath_document_storage_path.py

@@ -1,73 +0,0 @@
-# Generated by Django 4.0.4 on 2022-05-02 15:56
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1018_alter_savedviewfilterrule_value"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="StoragePath",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "name",
-                    models.CharField(max_length=128, unique=True, verbose_name="name"),
-                ),
-                (
-                    "match",
-                    models.CharField(blank=True, max_length=256, verbose_name="match"),
-                ),
-                (
-                    "matching_algorithm",
-                    models.PositiveIntegerField(
-                        choices=[
-                            (1, "Any word"),
-                            (2, "All words"),
-                            (3, "Exact match"),
-                            (4, "Regular expression"),
-                            (5, "Fuzzy word"),
-                            (6, "Automatic"),
-                        ],
-                        default=1,
-                        verbose_name="matching algorithm",
-                    ),
-                ),
-                (
-                    "is_insensitive",
-                    models.BooleanField(default=True, verbose_name="is insensitive"),
-                ),
-                ("path", models.CharField(max_length=512, verbose_name="path")),
-            ],
-            options={
-                "verbose_name": "storage path",
-                "verbose_name_plural": "storage paths",
-                "ordering": ("name",),
-            },
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="storage_path",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="documents",
-                to="documents.storagepath",
-                verbose_name="storage path",
-            ),
-        ),
-    ]

src/documents/migrations/1019_uisettings.py

@@ -1,39 +0,0 @@
-# Generated by Django 4.0.4 on 2022-05-07 05:10
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1018_alter_savedviewfilterrule_value"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="UiSettings",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("settings", models.JSONField(null=True)),
-                (
-                    "user",
-                    models.OneToOneField(
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="ui_settings",
-                        to=settings.AUTH_USER_MODEL,
-                    ),
-                ),
-            ],
-        ),
-    ]

src/documents/migrations/1020_merge_20220518_1839.py

@@ -1,12 +0,0 @@
-# Generated by Django 4.0.4 on 2022-05-18 18:39
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1019_storagepath_document_storage_path"),
-        ("documents", "1019_uisettings"),
-    ]
-
-    operations = []

src/documents/migrations/1021_webp_thumbnail_conversion.py

@@ -1,104 +0,0 @@
-# Generated by Django 4.0.5 on 2022-06-11 15:40
-import logging
-import multiprocessing.pool
-import shutil
-import tempfile
-import time
-from pathlib import Path
-
-from django.conf import settings
-from django.db import migrations
-
-from documents.parsers import run_convert
-
-logger = logging.getLogger("paperless.migrations")
-
-
-def _do_convert(work_package):
-    existing_thumbnail, converted_thumbnail = work_package
-    try:
-        logger.info(f"Converting thumbnail: {existing_thumbnail}")
-
-        # Run actual conversion
-        run_convert(
-            density=300,
-            scale="500x5000>",
-            alpha="remove",
-            strip=True,
-            trim=False,
-            auto_orient=True,
-            input_file=f"{existing_thumbnail}[0]",
-            output_file=str(converted_thumbnail),
-        )
-
-        # Copy newly created thumbnail to thumbnail directory
-        shutil.copy(converted_thumbnail, existing_thumbnail.parent)
-
-        # Remove the PNG version
-        existing_thumbnail.unlink()
-
-        logger.info(
-            "Conversion to WebP completed, "
-            f"replaced {existing_thumbnail.name} with {converted_thumbnail.name}",
-        )
-
-    except Exception as e:
-        logger.error(f"Error converting thumbnail (existing file unchanged): {e}")
-
-
-def _convert_thumbnails_to_webp(apps, schema_editor):
-    start = time.time()
-
-    with tempfile.TemporaryDirectory() as tempdir:
-        work_packages = []
-
-        for file in Path(settings.THUMBNAIL_DIR).glob("*.png"):
-            existing_thumbnail = file.resolve()
-
-            # Change the existing filename suffix from png to webp
-            converted_thumbnail_name = existing_thumbnail.with_suffix(
-                ".webp",
-            ).name
-
-            # Create the expected output filename in the tempdir
-            converted_thumbnail = (
-                Path(tempdir) / Path(converted_thumbnail_name)
-            ).resolve()
-
-            # Package up the necessary info
-            work_packages.append(
-                (existing_thumbnail, converted_thumbnail),
-            )
-
-        if work_packages:
-            logger.info(
-                "\n\n"
-                "  This is a one-time only migration to convert thumbnails for all of your\n"
-                "  documents into WebP format.  If you have a lot of documents though, \n"
-                "  this may take a while, so a coffee break may be in order."
-                "\n",
-            )
-
-            with multiprocessing.pool.Pool(
-                processes=min(multiprocessing.cpu_count(), 4),
-                maxtasksperchild=4,
-            ) as pool:
-                pool.map(_do_convert, work_packages)
-
-                end = time.time()
-                duration = end - start
-
-            logger.info(f"Conversion completed in {duration:.3f}s")
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1020_merge_20220518_1839"),
-    ]
-
-    operations = [
-        migrations.RunPython(
-            code=_convert_thumbnails_to_webp,
-            reverse_code=migrations.RunPython.noop,
-        ),
-    ]

src/documents/migrations/1022_paperlesstask.py

@@ -1,52 +0,0 @@
-# Generated by Django 4.0.4 on 2022-05-23 07:14
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1021_webp_thumbnail_conversion"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="PaperlessTask",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("task_id", models.CharField(max_length=128)),
-                ("name", models.CharField(max_length=256, null=True)),
-                (
-                    "created",
-                    models.DateTimeField(auto_now=True, verbose_name="created"),
-                ),
-                (
-                    "started",
-                    models.DateTimeField(null=True, verbose_name="started"),
-                ),
-                ("acknowledged", models.BooleanField(default=False)),
-                (
-                    "attempted_task",
-                    models.OneToOneField(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="attempted_task",
-                        # This is a dummy field, 1026 will fix up the column
-                        # This manual change is required, as django doesn't django doesn't really support
-                        # removing an app which has migration deps like this
-                        to="documents.document",
-                    ),
-                ),
-            ],
-        ),
-    ]

src/documents/migrations/1022_paperlesstask_squashed_1036_alter_savedviewfilterrule_rule_type.py

@@ -1,668 +0,0 @@
-# Generated by Django 4.2.13 on 2024-06-28 18:10
-
-import django.core.validators
-import django.db.models.deletion
-import django.utils.timezone
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    replaces = [
-        ("documents", "1022_paperlesstask"),
-        ("documents", "1023_add_comments"),
-        ("documents", "1024_document_original_filename"),
-        ("documents", "1025_alter_savedviewfilterrule_rule_type"),
-        ("documents", "1026_transition_to_celery"),
-        ("documents", "1027_remove_paperlesstask_attempted_task_and_more"),
-        ("documents", "1028_remove_paperlesstask_task_args_and_more"),
-        ("documents", "1029_alter_document_archive_serial_number"),
-        ("documents", "1030_alter_paperlesstask_task_file_name"),
-        ("documents", "1031_remove_savedview_user_correspondent_owner_and_more"),
-        ("documents", "1032_alter_correspondent_matching_algorithm_and_more"),
-        ("documents", "1033_alter_documenttype_options_alter_tag_options_and_more"),
-        ("documents", "1034_alter_savedviewfilterrule_rule_type"),
-        ("documents", "1035_rename_comment_note"),
-        ("documents", "1036_alter_savedviewfilterrule_rule_type"),
-    ]
-
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("django_celery_results", "0011_taskresult_periodic_task_name"),
-        ("documents", "1021_webp_thumbnail_conversion"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="Comment",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "comment",
-                    models.TextField(
-                        blank=True,
-                        help_text="Comment for the document",
-                        verbose_name="content",
-                    ),
-                ),
-                (
-                    "created",
-                    models.DateTimeField(
-                        db_index=True,
-                        default=django.utils.timezone.now,
-                        verbose_name="created",
-                    ),
-                ),
-                (
-                    "document",
-                    models.ForeignKey(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="documents",
-                        to="documents.document",
-                        verbose_name="document",
-                    ),
-                ),
-                (
-                    "user",
-                    models.ForeignKey(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.SET_NULL,
-                        related_name="users",
-                        to=settings.AUTH_USER_MODEL,
-                        verbose_name="user",
-                    ),
-                ),
-            ],
-            options={
-                "verbose_name": "comment",
-                "verbose_name_plural": "comments",
-                "ordering": ("created",),
-            },
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="original_filename",
-            field=models.CharField(
-                default=None,
-                editable=False,
-                help_text="The original name of the file when it was uploaded",
-                max_length=1024,
-                null=True,
-                verbose_name="original filename",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-        migrations.CreateModel(
-            name="PaperlessTask",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                ("task_id", models.CharField(max_length=128)),
-                ("acknowledged", models.BooleanField(default=False)),
-                (
-                    "attempted_task",
-                    models.OneToOneField(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="attempted_task",
-                        to="django_celery_results.taskresult",
-                    ),
-                ),
-            ],
-        ),
-        migrations.RunSQL(
-            sql="DROP TABLE IF EXISTS django_q_ormq",
-            reverse_sql="",
-        ),
-        migrations.RunSQL(
-            sql="DROP TABLE IF EXISTS django_q_schedule",
-            reverse_sql="",
-        ),
-        migrations.RunSQL(
-            sql="DROP TABLE IF EXISTS django_q_task",
-            reverse_sql="",
-        ),
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="attempted_task",
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_created",
-            field=models.DateTimeField(
-                default=django.utils.timezone.now,
-                help_text="Datetime field when the task result was created in UTC",
-                null=True,
-                verbose_name="Created DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_done",
-            field=models.DateTimeField(
-                default=None,
-                help_text="Datetime field when the task was completed in UTC",
-                null=True,
-                verbose_name="Completed DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_started",
-            field=models.DateTimeField(
-                default=None,
-                help_text="Datetime field when the task was started in UTC",
-                null=True,
-                verbose_name="Started DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="result",
-            field=models.TextField(
-                default=None,
-                help_text="The data returned by the task",
-                null=True,
-                verbose_name="Result Data",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="status",
-            field=models.CharField(
-                choices=[
-                    ("FAILURE", "FAILURE"),
-                    ("PENDING", "PENDING"),
-                    ("RECEIVED", "RECEIVED"),
-                    ("RETRY", "RETRY"),
-                    ("REVOKED", "REVOKED"),
-                    ("STARTED", "STARTED"),
-                    ("SUCCESS", "SUCCESS"),
-                ],
-                default="PENDING",
-                help_text="Current state of the task being run",
-                max_length=30,
-                verbose_name="Task State",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_name",
-            field=models.CharField(
-                help_text="Name of the Task which was run",
-                max_length=255,
-                null=True,
-                verbose_name="Task Name",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="paperlesstask",
-            name="acknowledged",
-            field=models.BooleanField(
-                default=False,
-                help_text="If the task is acknowledged via the frontend or API",
-                verbose_name="Acknowledged",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="paperlesstask",
-            name="task_id",
-            field=models.CharField(
-                help_text="Celery ID for the Task that was run",
-                max_length=255,
-                unique=True,
-                verbose_name="Task ID",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="document",
-            name="archive_serial_number",
-            field=models.PositiveIntegerField(
-                blank=True,
-                db_index=True,
-                help_text="The position of this document in your physical document archive.",
-                null=True,
-                unique=True,
-                validators=[
-                    django.core.validators.MaxValueValidator(4294967295),
-                    django.core.validators.MinValueValidator(0),
-                ],
-                verbose_name="archive serial number",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_file_name",
-            field=models.CharField(
-                help_text="Name of the file which the Task was run for",
-                max_length=255,
-                null=True,
-                verbose_name="Task Filename",
-            ),
-        ),
-        migrations.RenameField(
-            model_name="savedview",
-            old_name="user",
-            new_name="owner",
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="correspondent",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="documenttype",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="storagepath",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="storagepath",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterModelOptions(
-            name="documenttype",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "document type",
-                "verbose_name_plural": "document types",
-            },
-        ),
-        migrations.AlterModelOptions(
-            name="tag",
-            options={
-                "ordering": ("name",),
-                "verbose_name": "tag",
-                "verbose_name_plural": "tags",
-            },
-        ),
-        migrations.AlterField(
-            model_name="correspondent",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="storagepath",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="name",
-            field=models.CharField(max_length=128, verbose_name="name"),
-        ),
-        migrations.AddConstraint(
-            model_name="correspondent",
-            constraint=models.UniqueConstraint(
-                fields=("name", "owner"),
-                name="documents_correspondent_unique_name_owner",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="correspondent",
-            constraint=models.UniqueConstraint(
-                condition=models.Q(("owner__isnull", True)),
-                fields=("name",),
-                name="documents_correspondent_name_uniq",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="documenttype",
-            constraint=models.UniqueConstraint(
-                fields=("name", "owner"),
-                name="documents_documenttype_unique_name_owner",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="documenttype",
-            constraint=models.UniqueConstraint(
-                condition=models.Q(("owner__isnull", True)),
-                fields=("name",),
-                name="documents_documenttype_name_uniq",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="storagepath",
-            constraint=models.UniqueConstraint(
-                fields=("name", "owner"),
-                name="documents_storagepath_unique_name_owner",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="storagepath",
-            constraint=models.UniqueConstraint(
-                condition=models.Q(("owner__isnull", True)),
-                fields=("name",),
-                name="documents_storagepath_name_uniq",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="tag",
-            constraint=models.UniqueConstraint(
-                fields=("name", "owner"),
-                name="documents_tag_unique_name_owner",
-            ),
-        ),
-        migrations.AddConstraint(
-            model_name="tag",
-            constraint=models.UniqueConstraint(
-                condition=models.Q(("owner__isnull", True)),
-                fields=("name",),
-                name="documents_tag_name_uniq",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                    (26, "has correspondent in"),
-                    (27, "does not have correspondent in"),
-                    (28, "has document type in"),
-                    (29, "does not have document type in"),
-                    (30, "has storage path in"),
-                    (31, "does not have storage path in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-        migrations.RenameModel(
-            old_name="Comment",
-            new_name="Note",
-        ),
-        migrations.RenameField(
-            model_name="note",
-            old_name="comment",
-            new_name="note",
-        ),
-        migrations.AlterModelOptions(
-            name="note",
-            options={
-                "ordering": ("created",),
-                "verbose_name": "note",
-                "verbose_name_plural": "notes",
-            },
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="document",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="notes",
-                to="documents.document",
-                verbose_name="document",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="note",
-            field=models.TextField(
-                blank=True,
-                help_text="Note for the document",
-                verbose_name="content",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="user",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="notes",
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="user",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                    (26, "has correspondent in"),
-                    (27, "does not have correspondent in"),
-                    (28, "has document type in"),
-                    (29, "does not have document type in"),
-                    (30, "has storage path in"),
-                    (31, "does not have storage path in"),
-                    (32, "owner is"),
-                    (33, "has owner in"),
-                    (34, "does not have owner"),
-                    (35, "does not have owner in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1023_add_comments.py

@@ -1,70 +0,0 @@
-import django.utils.timezone
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1022_paperlesstask"),
-    ]
-
-    operations = [
-        migrations.CreateModel(
-            name="Comment",
-            fields=[
-                (
-                    "id",
-                    models.AutoField(
-                        auto_created=True,
-                        primary_key=True,
-                        serialize=False,
-                        verbose_name="ID",
-                    ),
-                ),
-                (
-                    "comment",
-                    models.TextField(
-                        blank=True,
-                        help_text="Comment for the document",
-                        verbose_name="content",
-                    ),
-                ),
-                (
-                    "created",
-                    models.DateTimeField(
-                        db_index=True,
-                        default=django.utils.timezone.now,
-                        verbose_name="created",
-                    ),
-                ),
-                (
-                    "document",
-                    models.ForeignKey(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.CASCADE,
-                        related_name="documents",
-                        to="documents.document",
-                        verbose_name="document",
-                    ),
-                ),
-                (
-                    "user",
-                    models.ForeignKey(
-                        blank=True,
-                        null=True,
-                        on_delete=django.db.models.deletion.SET_NULL,
-                        related_name="users",
-                        to=settings.AUTH_USER_MODEL,
-                        verbose_name="user",
-                    ),
-                ),
-            ],
-            options={
-                "verbose_name": "comment",
-                "verbose_name_plural": "comments",
-                "ordering": ("created",),
-            },
-        ),
-    ]

src/documents/migrations/1024_document_original_filename.py

@@ -1,25 +0,0 @@
-# Generated by Django 4.0.6 on 2022-07-25 06:34
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1023_add_comments"),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name="document",
-            name="original_filename",
-            field=models.CharField(
-                default=None,
-                editable=False,
-                help_text="The original name of the file when it was uploaded",
-                max_length=1024,
-                null=True,
-                verbose_name="original filename",
-            ),
-        ),
-    ]

src/documents/migrations/1025_alter_savedviewfilterrule_rule_type.py

@@ -1,48 +0,0 @@
-# Generated by Django 4.0.5 on 2022-08-26 16:49
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1024_document_original_filename"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1026_transition_to_celery.py

@@ -1,60 +0,0 @@
-# Generated by Django 4.1.1 on 2022-09-27 19:31
-
-import django.db.models.deletion
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("django_celery_results", "0011_taskresult_periodic_task_name"),
-        ("documents", "1025_alter_savedviewfilterrule_rule_type"),
-    ]
-
-    operations = [
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="created",
-        ),
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="name",
-        ),
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="started",
-        ),
-        # Remove the field from the model
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="attempted_task",
-        ),
-        # Add the field back, pointing to the correct model
-        # This resolves a problem where the temporary change in 1022
-        # results in a type mismatch
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="attempted_task",
-            field=models.OneToOneField(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="attempted_task",
-                to="django_celery_results.taskresult",
-            ),
-        ),
-        # Drop the django-q tables entirely
-        # Must be done last or there could be references here
-        migrations.RunSQL(
-            "DROP TABLE IF EXISTS django_q_ormq",
-            reverse_sql=migrations.RunSQL.noop,
-        ),
-        migrations.RunSQL(
-            "DROP TABLE IF EXISTS django_q_schedule",
-            reverse_sql=migrations.RunSQL.noop,
-        ),
-        migrations.RunSQL(
-            "DROP TABLE IF EXISTS django_q_task",
-            reverse_sql=migrations.RunSQL.noop,
-        ),
-    ]

src/documents/migrations/1027_remove_paperlesstask_attempted_task_and_more.py

@@ -1,134 +0,0 @@
-# Generated by Django 4.1.2 on 2022-10-17 16:31
-
-import django.utils.timezone
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1026_transition_to_celery"),
-    ]
-
-    operations = [
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="attempted_task",
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_created",
-            field=models.DateTimeField(
-                default=django.utils.timezone.now,
-                help_text="Datetime field when the task result was created in UTC",
-                null=True,
-                verbose_name="Created DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_done",
-            field=models.DateTimeField(
-                default=None,
-                help_text="Datetime field when the task was completed in UTC",
-                null=True,
-                verbose_name="Completed DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="date_started",
-            field=models.DateTimeField(
-                default=None,
-                help_text="Datetime field when the task was started in UTC",
-                null=True,
-                verbose_name="Started DateTime",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="result",
-            field=models.TextField(
-                default=None,
-                help_text="The data returned by the task",
-                null=True,
-                verbose_name="Result Data",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="status",
-            field=models.CharField(
-                choices=[
-                    ("FAILURE", "FAILURE"),
-                    ("PENDING", "PENDING"),
-                    ("RECEIVED", "RECEIVED"),
-                    ("RETRY", "RETRY"),
-                    ("REVOKED", "REVOKED"),
-                    ("STARTED", "STARTED"),
-                    ("SUCCESS", "SUCCESS"),
-                ],
-                default="PENDING",
-                help_text="Current state of the task being run",
-                max_length=30,
-                verbose_name="Task State",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_args",
-            field=models.JSONField(
-                help_text="JSON representation of the positional arguments used with the task",
-                null=True,
-                verbose_name="Task Positional Arguments",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_file_name",
-            field=models.CharField(
-                help_text="Name of the file which the Task was run for",
-                max_length=255,
-                null=True,
-                verbose_name="Task Name",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_kwargs",
-            field=models.JSONField(
-                help_text="JSON representation of the named arguments used with the task",
-                null=True,
-                verbose_name="Task Named Arguments",
-            ),
-        ),
-        migrations.AddField(
-            model_name="paperlesstask",
-            name="task_name",
-            field=models.CharField(
-                help_text="Name of the Task which was run",
-                max_length=255,
-                null=True,
-                verbose_name="Task Name",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="paperlesstask",
-            name="acknowledged",
-            field=models.BooleanField(
-                default=False,
-                help_text="If the task is acknowledged via the frontend or API",
-                verbose_name="Acknowledged",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="paperlesstask",
-            name="task_id",
-            field=models.CharField(
-                help_text="Celery ID for the Task that was run",
-                max_length=255,
-                unique=True,
-                verbose_name="Task ID",
-            ),
-        ),
-    ]

src/documents/migrations/1028_remove_paperlesstask_task_args_and_more.py

@@ -1,20 +0,0 @@
-# Generated by Django 4.1.3 on 2022-11-22 17:50
-
-from django.db import migrations
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1027_remove_paperlesstask_attempted_task_and_more"),
-    ]
-
-    operations = [
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="task_args",
-        ),
-        migrations.RemoveField(
-            model_name="paperlesstask",
-            name="task_kwargs",
-        ),
-    ]

src/documents/migrations/1029_alter_document_archive_serial_number.py

@@ -1,30 +0,0 @@
-# Generated by Django 4.1.4 on 2023-01-24 17:56
-
-import django.core.validators
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1028_remove_paperlesstask_task_args_and_more"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="archive_serial_number",
-            field=models.PositiveIntegerField(
-                blank=True,
-                db_index=True,
-                help_text="The position of this document in your physical document archive.",
-                null=True,
-                unique=True,
-                validators=[
-                    django.core.validators.MaxValueValidator(4294967295),
-                    django.core.validators.MinValueValidator(0),
-                ],
-                verbose_name="archive serial number",
-            ),
-        ),
-    ]

src/documents/migrations/1030_alter_paperlesstask_task_file_name.py

@@ -1,23 +0,0 @@
-# Generated by Django 4.1.5 on 2023-02-03 21:53
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1029_alter_document_archive_serial_number"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="paperlesstask",
-            name="task_file_name",
-            field=models.CharField(
-                help_text="Name of the file which the Task was run for",
-                max_length=255,
-                null=True,
-                verbose_name="Task Filename",
-            ),
-        ),
-    ]

src/documents/migrations/1031_remove_savedview_user_correspondent_owner_and_more.py

@@ -1,87 +0,0 @@
-# Generated by Django 4.1.4 on 2022-02-03 04:24
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1030_alter_paperlesstask_task_file_name"),
-    ]
-
-    operations = [
-        migrations.RenameField(
-            model_name="savedview",
-            old_name="user",
-            new_name="owner",
-        ),
-        migrations.AlterField(
-            model_name="savedview",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="correspondent",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="document",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="documenttype",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="storagepath",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-        migrations.AddField(
-            model_name="tag",
-            name="owner",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="owner",
-            ),
-        ),
-    ]

src/documents/migrations/1032_alter_correspondent_matching_algorithm_and_more.py

@@ -1,81 +0,0 @@
-# Generated by Django 4.1.7 on 2023-02-22 00:45
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1031_remove_savedview_user_correspondent_owner_and_more"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="correspondent",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="documenttype",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="storagepath",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="tag",
-            name="matching_algorithm",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "None"),
-                    (1, "Any word"),
-                    (2, "All words"),
-                    (3, "Exact match"),
-                    (4, "Regular expression"),
-                    (5, "Fuzzy word"),
-                    (6, "Automatic"),
-                ],
-                default=1,
-                verbose_name="matching algorithm",
-            ),
-        ),
-    ]

src/documents/migrations/1034_alter_savedviewfilterrule_rule_type.py

@@ -1,54 +0,0 @@
-# Generated by Django 4.1.5 on 2023-03-15 07:10
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1033_alter_documenttype_options_alter_tag_options_and_more"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                    (26, "has correspondent in"),
-                    (27, "does not have correspondent in"),
-                    (28, "has document type in"),
-                    (29, "does not have document type in"),
-                    (30, "has storage path in"),
-                    (31, "does not have storage path in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]

src/documents/migrations/1035_rename_comment_note.py

@@ -1,62 +0,0 @@
-# Generated by Django 4.1.5 on 2023-03-17 22:15
-
-import django.db.models.deletion
-from django.conf import settings
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
-        ("documents", "1034_alter_savedviewfilterrule_rule_type"),
-    ]
-
-    operations = [
-        migrations.RenameModel(
-            old_name="Comment",
-            new_name="Note",
-        ),
-        migrations.RenameField(model_name="note", old_name="comment", new_name="note"),
-        migrations.AlterModelOptions(
-            name="note",
-            options={
-                "ordering": ("created",),
-                "verbose_name": "note",
-                "verbose_name_plural": "notes",
-            },
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="document",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.CASCADE,
-                related_name="notes",
-                to="documents.document",
-                verbose_name="document",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="note",
-            field=models.TextField(
-                blank=True,
-                help_text="Note for the document",
-                verbose_name="content",
-            ),
-        ),
-        migrations.AlterField(
-            model_name="note",
-            name="user",
-            field=models.ForeignKey(
-                blank=True,
-                null=True,
-                on_delete=django.db.models.deletion.SET_NULL,
-                related_name="notes",
-                to=settings.AUTH_USER_MODEL,
-                verbose_name="user",
-            ),
-        ),
-    ]

src/documents/migrations/1036_alter_savedviewfilterrule_rule_type.py

@@ -1,58 +0,0 @@
-# Generated by Django 4.1.7 on 2023-05-04 04:11
-
-from django.db import migrations
-from django.db import models
-
-
-class Migration(migrations.Migration):
-    dependencies = [
-        ("documents", "1035_rename_comment_note"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="savedviewfilterrule",
-            name="rule_type",
-            field=models.PositiveIntegerField(
-                choices=[
-                    (0, "title contains"),
-                    (1, "content contains"),
-                    (2, "ASN is"),
-                    (3, "correspondent is"),
-                    (4, "document type is"),
-                    (5, "is in inbox"),
-                    (6, "has tag"),
-                    (7, "has any tag"),
-                    (8, "created before"),
-                    (9, "created after"),
-                    (10, "created year is"),
-                    (11, "created month is"),
-                    (12, "created day is"),
-                    (13, "added before"),
-                    (14, "added after"),
-                    (15, "modified before"),
-                    (16, "modified after"),
-                    (17, "does not have tag"),
-                    (18, "does not have ASN"),
-                    (19, "title or content contains"),
-                    (20, "fulltext query"),
-                    (21, "more like this"),
-                    (22, "has tags in"),
-                    (23, "ASN greater than"),
-                    (24, "ASN less than"),
-                    (25, "storage path is"),
-                    (26, "has correspondent in"),
-                    (27, "does not have correspondent in"),
-                    (28, "has document type in"),
-                    (29, "does not have document type in"),
-                    (30, "has storage path in"),
-                    (31, "does not have storage path in"),
-                    (32, "owner is"),
-                    (33, "has owner in"),
-                    (34, "does not have owner"),
-                    (35, "does not have owner in"),
-                ],
-                verbose_name="rule type",
-            ),
-        ),
-    ]