Feature: Replace Whoosh with tantivy search backend (#12471)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Antoine Mérino <3023499+Merinorus@users.noreply.github.com>

src/documents/sanity_checker.py

@@ -9,19 +9,14 @@ to wrap the document queryset (e.g., with a progress bar). The default
 is an identity function that adds no overhead.
 """
 
-from __future__ import annotations
-
 import logging
 import uuid
 from collections import defaultdict
-from collections.abc import Callable
-from collections.abc import Iterable
 from collections.abc import Iterator
 from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Final
 from typing import TypedDict
-from typing import TypeVar
 
 from celery import states
 from django.conf import settings
@@ -29,14 +24,13 @@ from django.utils import timezone
 
 from documents.models import Document
 from documents.models import PaperlessTask
+from documents.utils import IterWrapper
 from documents.utils import compute_checksum
+from documents.utils import identity
 from paperless.config import GeneralConfig
 
 logger = logging.getLogger("paperless.sanity_checker")
 
-_T = TypeVar("_T")
-IterWrapper = Callable[[Iterable[_T]], Iterable[_T]]
-
 
 class MessageEntry(TypedDict):
     """A single sanity check message with its severity level."""
@@ -45,11 +39,6 @@ class MessageEntry(TypedDict):
     message: str
 
 
-def _identity(iterable: Iterable[_T]) -> Iterable[_T]:
-    """Pass through an iterable unchanged (default iter_wrapper)."""
-    return iterable
-
-
 class SanityCheckMessages:
     """Collects sanity check messages grouped by document primary key.
 
@@ -296,7 +285,7 @@ def _check_document(
 def check_sanity(
     *,
     scheduled: bool = True,
-    iter_wrapper: IterWrapper[Document] = _identity,
+    iter_wrapper: IterWrapper[Document] = identity,
 ) -> SanityCheckMessages:
     """Run a full sanity check on the document archive.