fixup! refactor(search): derive build_schema() from shared PUBLIC_FIELDS table

src/documents/search/_backend.py

@@ -506,7 +506,6 @@ class TantivyBackend:
             doc.add_text("correspondent_sort", document.correspondent.name)
             if cjk_corr := extract_cjk_text(document.correspondent.name):
                 doc.add_text("bigram_correspondent", cjk_corr)
-            doc.add_unsigned("correspondent_id", document.correspondent_id)
 
         # Document type
         if document.document_type:
@@ -514,12 +513,10 @@ class TantivyBackend:
             doc.add_text("type_sort", document.document_type.name)
             if cjk_type := extract_cjk_text(document.document_type.name):
                 doc.add_text("bigram_document_type", cjk_type)
-            doc.add_unsigned("document_type_id", document.document_type_id)
 
         # Storage path
         if document.storage_path:
             doc.add_text("storage_path", document.storage_path.name)
-            doc.add_unsigned("storage_path_id", document.storage_path_id)
 
         # Tags — collect names for autocomplete in the same pass
         tag_names: list[str] = []
@@ -527,7 +524,6 @@ class TantivyBackend:
             doc.add_text("tag", tag.name)
             if cjk_tag := extract_cjk_text(tag.name):
                 doc.add_text("bigram_tag", cjk_tag)
-            doc.add_unsigned("tag_id", tag.pk)
             tag_names.append(tag.name)
 
         # Notes — JSON for structured queries (notes.user:alice, notes.note:text).

src/documents/search/_schema.py

@@ -19,7 +19,11 @@ if TYPE_CHECKING:
 logger = logging.getLogger("paperless.search")
 
 # v1 - Initial tantivy schema format
-SCHEMA_VERSION: Final[int] = 1
+# v2 - build_schema() derived from PUBLIC_FIELDS, changing the field declaration
+#      order, and the write-only correspondent/document_type/storage_path/tag id
+#      columns dropped. tantivy compares schemas by ordered field list, so an
+#      index built by v1 rejects every write against the v2 schema.
+SCHEMA_VERSION: Final[int] = 2
 
 
 def build_schema() -> tantivy.Schema:
@@ -109,15 +113,8 @@ def build_schema() -> tantivy.Schema:
     # The stored value is never read back, so storing it only wastes space.
     sb.add_text_field("autocomplete_word", stored=False, tokenizer_name="raw")
 
-    for field in (
-        "correspondent_id",
-        "document_type_id",
-        "storage_path_id",
-        "tag_id",
-        "owner_id",
-        "viewer_id",
-        "viewer_group_id",
-    ):
+    # Permission filter columns, read by build_permission_filter.
+    for field in ("owner_id", "viewer_id", "viewer_group_id"):
         sb.add_unsigned_field(field, stored=False, indexed=True, fast=True)
 
     return sb.build()

src/documents/tests/search/test_permission_field_isolation.py

@@ -0,0 +1,148 @@
+"""Permission filtering must hold against the real indexed document shape.
+
+Only three of the index's unsigned ``*_id`` columns are load-bearing:
+``owner_id``, ``viewer_id`` and ``viewer_group_id``, all read by
+build_permission_filter. The rest (correspondent/document_type/storage_path/tag
+ids) were written on every document and read by nothing, and were dropped.
+
+These tests index real Documents through the backend's own document builder and
+assert result-level visibility per user, so a mistake about which columns are
+load-bearing shows up as documents leaking across users rather than as a passing
+unit test over a hand-built index.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+from django.contrib.auth.models import Group
+from django.contrib.auth.models import User
+from guardian.shortcuts import assign_perm
+
+from documents.models import Correspondent
+from documents.models import Document
+from documents.models import DocumentType
+from documents.models import StoragePath
+from documents.models import Tag
+
+if TYPE_CHECKING:
+    from documents.search._backend import TantivyBackend
+
+pytestmark = [pytest.mark.search, pytest.mark.django_db]
+
+
+@pytest.fixture
+def owner() -> User:
+    return User.objects.create_user(username="owner")
+
+
+@pytest.fixture
+def stranger() -> User:
+    return User.objects.create_user(username="stranger")
+
+
+@pytest.fixture
+def viewer() -> User:
+    return User.objects.create_user(username="viewer")
+
+
+@pytest.fixture
+def group_member() -> User:
+    user = User.objects.create_user(username="group_member")
+    user.groups.add(Group.objects.create(name="accounting"))
+    return user
+
+
+class TestPermissionFilteringOnIndexedDocuments:
+    def test_unowned_document_is_visible_to_everyone(
+        self,
+        backend: TantivyBackend,
+        stranger: User,
+    ) -> None:
+        doc = Document.objects.create(
+            title="Public Invoice",
+            content="invoice total due",
+            checksum="perm-unowned",
+        )
+        backend.add_or_update(doc)
+
+        assert backend.search_ids("invoice", user=stranger) == [doc.pk]
+
+    def test_owned_document_is_visible_only_to_its_owner(
+        self,
+        backend: TantivyBackend,
+        owner: User,
+        stranger: User,
+    ) -> None:
+        doc = Document.objects.create(
+            title="Private Invoice",
+            content="invoice total due",
+            checksum="perm-owned",
+            owner=owner,
+        )
+        backend.add_or_update(doc)
+
+        assert backend.search_ids("invoice", user=owner) == [doc.pk]
+        assert backend.search_ids("invoice", user=stranger) == []
+
+    def test_explicitly_shared_document_is_visible_to_the_viewer(
+        self,
+        backend: TantivyBackend,
+        owner: User,
+        viewer: User,
+        stranger: User,
+    ) -> None:
+        doc = Document.objects.create(
+            title="Shared Invoice",
+            content="invoice total due",
+            checksum="perm-shared-user",
+            owner=owner,
+        )
+        assign_perm("view_document", viewer, doc)
+        backend.add_or_update(doc)
+
+        assert backend.search_ids("invoice", user=viewer) == [doc.pk]
+        assert backend.search_ids("invoice", user=stranger) == []
+
+    def test_group_shared_document_is_visible_to_group_members(
+        self,
+        backend: TantivyBackend,
+        owner: User,
+        group_member: User,
+        stranger: User,
+    ) -> None:
+        doc = Document.objects.create(
+            title="Group Invoice",
+            content="invoice total due",
+            checksum="perm-shared-group",
+            owner=owner,
+        )
+        assign_perm("view_document", group_member.groups.first(), doc)
+        backend.add_or_update(doc)
+
+        assert backend.search_ids("invoice", user=group_member) == [doc.pk]
+        assert backend.search_ids("invoice", user=stranger) == []
+
+    def test_metadata_does_not_widen_visibility(
+        self,
+        backend: TantivyBackend,
+        owner: User,
+        stranger: User,
+    ) -> None:
+        """A document carrying correspondent/type/storage-path/tag metadata is
+        still filtered by owner alone."""
+        doc = Document.objects.create(
+            title="Tagged Invoice",
+            content="invoice total due",
+            checksum="perm-metadata",
+            owner=owner,
+            correspondent=Correspondent.objects.create(name="ACME"),
+            document_type=DocumentType.objects.create(name="Bill"),
+            storage_path=StoragePath.objects.create(name="Archive", path="archive/"),
+        )
+        doc.tags.add(Tag.objects.create(name="paid"))
+        backend.add_or_update(doc)
+
+        assert backend.search_ids("invoice", user=owner) == [doc.pk]
+        assert backend.search_ids("invoice", user=stranger) == []

src/documents/tests/search/test_schema_version.py

@@ -0,0 +1,164 @@
+"""SCHEMA_VERSION must change whenever build_schema()'s field list or order does.
+
+tantivy compares schemas by *ordered* field list. ``Index.open()`` loads the
+schema from the index's own ``meta.json``, so reads against an index built by an
+older release keep working after a field reorder. Writes do not:
+``WriteBatch.__enter__`` calls ``tantivy.Index(build_schema(), path=...)``, an
+open-or-create that raises ``ValueError`` on any schema difference. Nothing
+catches that ValueError, so consumption, index_document and bulk edit all
+hard-fail while ``/api/status/`` still reports the index healthy.
+
+The only thing that saves such an install is ``needs_rebuild()`` noticing the
+version stamped in ``.index_settings.json`` is stale.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import TYPE_CHECKING
+
+import pytest
+import tantivy
+from django.conf import settings as django_settings
+
+from documents.search._schema import build_schema
+from documents.search._schema import needs_rebuild
+from documents.search._schema import open_or_rebuild_index
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+pytestmark = [pytest.mark.search]
+
+RELEASED_V1_SCHEMA_VERSION = 1
+
+
+def _build_released_v1_schema() -> tantivy.Schema:
+    """Frozen copy of build_schema() as shipped in v3.0.x (schema version 1).
+
+    Deliberately duplicated rather than imported: it must keep describing the
+    on-disk layout of already-deployed indexes even as build_schema() evolves.
+    """
+    sb = tantivy.SchemaBuilder()
+
+    sb.add_unsigned_field("id", stored=True, indexed=True, fast=True)
+    sb.add_text_field("checksum", stored=True, tokenizer_name="raw")
+
+    for field in (
+        "title",
+        "correspondent",
+        "document_type",
+        "storage_path",
+        "original_filename",
+        "content",
+    ):
+        sb.add_text_field(field, stored=True, tokenizer_name="paperless_text")
+
+    for field in ("title_sort", "correspondent_sort", "type_sort"):
+        sb.add_text_field(
+            field,
+            stored=False,
+            tokenizer_name="simple_analyzer",
+            fast=True,
+        )
+
+    for field in (
+        "bigram_content",
+        "bigram_title",
+        "bigram_correspondent",
+        "bigram_document_type",
+        "bigram_tag",
+    ):
+        sb.add_text_field(field, stored=False, tokenizer_name="bigram_analyzer")
+
+    for field in ("simple_title", "simple_content"):
+        sb.add_text_field(field, stored=False, tokenizer_name="simple_search_analyzer")
+
+    sb.add_text_field("autocomplete_word", stored=False, tokenizer_name="raw")
+    sb.add_text_field("tag", stored=True, tokenizer_name="paperless_text")
+
+    sb.add_json_field("notes", stored=True, tokenizer_name="paperless_text")
+    sb.add_text_field("notes_text", stored=True, tokenizer_name="paperless_text")
+    sb.add_json_field("custom_fields", stored=True, tokenizer_name="paperless_text")
+
+    for field in (
+        "correspondent_id",
+        "document_type_id",
+        "storage_path_id",
+        "tag_id",
+        "owner_id",
+        "viewer_id",
+        "viewer_group_id",
+    ):
+        sb.add_unsigned_field(field, stored=False, indexed=True, fast=True)
+
+    for field in ("created", "modified", "added"):
+        sb.add_date_field(field, stored=True, indexed=True, fast=True)
+
+    for field in ("asn", "page_count", "num_notes"):
+        sb.add_unsigned_field(field, stored=True, indexed=True, fast=True)
+
+    return sb.build()
+
+
+@pytest.fixture
+def released_v1_index(tmp_path: Path) -> Path:
+    """An index directory as a v3.0.x install would leave it on disk."""
+    index_dir = tmp_path / "index"
+    index_dir.mkdir()
+    tantivy.Index(_build_released_v1_schema(), path=str(index_dir))
+    (index_dir / ".index_settings.json").write_text(
+        json.dumps(
+            {
+                "schema_version": RELEASED_V1_SCHEMA_VERSION,
+                "language": django_settings.SEARCH_LANGUAGE,
+            },
+        ),
+    )
+    return index_dir
+
+
+class TestUpgradeFromReleasedV1Index:
+    def test_released_v1_index_is_flagged_for_rebuild(
+        self,
+        released_v1_index: Path,
+    ) -> None:
+        """The current schema differs from v1's, so the sentinel must be stale.
+
+        If this fails, `document_index reindex --if-needed` prints "Search index
+        is up to date" and skips, leaving the mismatched index in place.
+        """
+        assert needs_rebuild(released_v1_index) is True
+
+    def test_v1_index_rejects_writes_against_the_current_schema(
+        self,
+        released_v1_index: Path,
+    ) -> None:
+        """The failure mode the version bump exists to prevent.
+
+        This is exactly what WriteBatch.__enter__ does on every index write.
+        """
+        with pytest.raises(ValueError, match="schema does not match"):
+            tantivy.Index(build_schema(), path=str(released_v1_index))
+
+    def test_opening_a_v1_index_leaves_it_writable(
+        self,
+        released_v1_index: Path,
+    ) -> None:
+        """End to end: open_or_rebuild_index must hand back an index that the
+        write path can reopen. Before the version bump, needs_rebuild() returned
+        False here, the stale directory survived untouched, and every subsequent
+        write raised the ValueError above."""
+        open_or_rebuild_index(released_v1_index)
+
+        tantivy.Index(build_schema(), path=str(released_v1_index))
+
+    def test_rebuilt_index_is_not_rebuilt_again(
+        self,
+        released_v1_index: Path,
+    ) -> None:
+        """The rebuild must stamp the version it actually wrote, otherwise every
+        startup wipes and reindexes the whole corpus."""
+        open_or_rebuild_index(released_v1_index)
+
+        assert needs_rebuild(released_v1_index) is False