Fix: prevent scale vs page loop in pngx PDF viewer (#13406)

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.component.spec.ts

@@ -129,13 +129,25 @@ describe('PngxPdfViewerComponent', () => {
     ;(component as any).applyScale()
     expect(viewer.currentScaleValue).toBe(PdfZoomScale.PageFit)
     expect(viewer.currentScale).toBe(2)
+  })
 
+  it('does not reapply scale for page-only changes', async () => {
+    await initComponent()
+
+    const pdf = (component as any).pdf as { numPages: number }
+    pdf.numPages = 3
+    const viewer = (component as any).pdfViewer as PDFViewer
+    viewer.setDocument(pdf)
     const applyScaleSpy = jest.spyOn(component as any, 'applyScale')
     component.page = 2
-    ;(component as any).lastViewerPage = 2
-    ;(component as any).applyViewerState()
+
+    component.ngOnChanges({
+      page: new SimpleChange(1, 2, false),
+    })
+
+    expect(viewer.currentPageNumber).toBe(2)
     expect((component as any).lastViewerPage).toBeUndefined()
-    expect(applyScaleSpy).toHaveBeenCalled()
+    expect(applyScaleSpy).not.toHaveBeenCalled()
   })
 
   it('does not reset the viewer when it is already on the requested page', async () => {

src-ui/src/app/components/common/pdf-viewer/pdf-viewer.component.ts

@@ -116,7 +116,10 @@ export class PngxPdfViewerComponent
       changes['zoomScale'] ||
       changes['rotation']
     ) {
-      this.applyViewerState()
+      // Prevent loop with page / scale application see https://github.com/paperless-ngx/paperless-ngx/issues/13404
+      this.applyViewerState(
+        !!(changes['zoom'] || changes['zoomScale'] || changes['rotation'])
+      )
     }
 
     if (changes['searchQuery']) {
@@ -240,7 +243,7 @@ export class PngxPdfViewerComponent
     }
   }
 
-  private applyViewerState(): void {
+  private applyViewerState(applyScale = true): void {
     if (!this.pdfViewer) {
       return
     }
@@ -264,7 +267,7 @@ export class PngxPdfViewerComponent
     if (this.page === this.lastViewerPage) {
       this.lastViewerPage = undefined
     }
-    if (hasPages) {
+    if (hasPages && applyScale) {
       this.applyScale()
     }
     this.dispatchFindIfReady()

src/documents/mail.py

@@ -36,6 +36,9 @@ def send_email(
 
     TODO: re-evaluate this pending https://code.djangoproject.com/ticket/35581 / https://github.com/django/django/pull/18966
     """
+    if "\r" in subject or "\n" in subject:
+        subject = " ".join(line.strip(" \t") for line in subject.splitlines())
+
     email = EmailMessage(
         subject=subject,
         body=body,

src/documents/management/commands/document_importer.py

@@ -386,10 +386,19 @@ class Command(CryptMixin, PaperlessCommand):
                 raise DeserializationError(
                     f"{model.__name__} has no updatable fields; PK-only models are not supported by the importer",
                 )
+            # MySQL/MariaDB support upserts via ON DUPLICATE KEY UPDATE but,
+            # unlike PostgreSQL/SQLite, cannot target a specific unique field
+            # for the conflict -- passing unique_fields there raises
+            # NotSupportedError.
+            unique_fields = (
+                [model._meta.pk.attname]
+                if connection.features.supports_update_conflicts_with_target
+                else None
+            )
             model.objects.bulk_create(  # type: ignore[attr-defined]
                 instances,
                 update_conflicts=True,
-                unique_fields=[model._meta.pk.attname],
+                unique_fields=unique_fields,
                 update_fields=update_fields,
             )
             loaded_models.add(model)

src/documents/tests/test_api_email.py

@@ -75,7 +75,7 @@ class TestEmail(DirectoriesMixin, SampleDirMixin, APITestCase):
                 {
                     "documents": [self.doc1.pk, self.doc2.pk],
                     "addresses": "hello@paperless-ngx.com,test@example.com",
-                    "subject": "Bulk email test",
+                    "subject": "Bulk email\n test",
                     "message": "Here are your documents",
                 },
             ),

src/paperless_ai/indexing.py

@@ -1,6 +1,5 @@
 import logging
 from collections.abc import Iterable
-from collections.abc import Iterator
 from contextlib import contextmanager
 from datetime import timedelta
 from typing import TYPE_CHECKING
@@ -23,7 +22,6 @@ from paperless_ai.embedding import get_configured_model_name
 from paperless_ai.embedding import get_embedding_model
 
 if TYPE_CHECKING:
-    from django.db.models import QuerySet
     from llama_index.core.schema import BaseNode
 
     from paperless_ai.vector_store import PaperlessSqliteVecVectorStore
@@ -34,35 +32,6 @@ logger = logging.getLogger("paperless_ai.indexing")
 RAG_NUM_OUTPUT = 512
 RAG_CHUNK_OVERLAP = 200
 
-# update_llm_index(): row count per .iterator() batch when streaming
-# documents for a rebuild/update, matching _DocumentViewerStream's chunk
-# size in documents/search/_backend.py.
-_INDEX_STREAM_CHUNK_SIZE = 1000
-
-
-class _StreamedDocuments:
-    """A thin QuerySet wrapper that streams via ``.iterator()`` instead of
-    materializing every row (plus its ``content`` and prefetch caches) into
-    memory at once, while still supporting ``len()`` so ``iter_wrapper``'s
-    progress bar shows a real total instead of falling back to indeterminate.
-    Same shape as ``documents/search/_backend.py``'s ``_DocumentViewerStream``,
-    just without that class's extra per-batch permission lookup -- nothing
-    here needs one.
-    """
-
-    def __init__(self, documents: "QuerySet[Document]") -> None:
-        self._documents = documents
-
-    def __len__(self) -> int:
-        return self._documents.count()
-
-    def __iter__(self) -> Iterator[Document]:
-        # iterator(chunk_size=...) streams from a server-side cursor instead
-        # of materializing the whole queryset in memory; since Django 4.1 it
-        # still honours prefetch_related, running the prefetches one batch
-        # at a time.
-        return iter(self._documents.iterator(chunk_size=_INDEX_STREAM_CHUNK_SIZE))
-
 
 def queue_llm_index_update_if_needed(*, rebuild: bool, reason: str) -> bool:
     # NOTE: The check-then-enqueue sequence below is non-atomic (TOCTOU): two
@@ -416,7 +385,7 @@ def update_llm_index(
         if rebuild or not store.table_exists():
             logger.info("Rebuilding LLM index.")
             store.drop_table()
-            for document in iter_wrapper(_StreamedDocuments(documents)):
+            for document in iter_wrapper(documents):
                 nodes = build_document_node(document, chunk_size=chunk_size)
                 _embed_nodes(nodes, embed_model)
                 store.add(nodes)
@@ -429,7 +398,7 @@ def update_llm_index(
             )
             existing = store.get_modified_times()
             changed = 0
-            for document in iter_wrapper(_StreamedDocuments(scoped_documents)):
+            for document in iter_wrapper(scoped_documents):
                 doc_id = str(document.id)
                 if existing.get(doc_id) == document.modified.isoformat():
                     continue

src/paperless_ai/tests/test_ai_indexing.py

@@ -186,57 +186,6 @@ def test_truncate_embedding_query_returns_single_chunk() -> None:
     assert "word199" not in result
 
 
-class TestStreamedDocuments:
-    """_StreamedDocuments streams via .iterator() instead of materializing
-    the whole queryset (plus its content and prefetch caches) in memory at
-    once, while still supporting len() so a progress bar wrapped around it
-    shows a real total.
-    """
-
-    def test_len_uses_queryset_count(
-        self,
-        mocker: pytest_mock.MockerFixture,
-    ) -> None:
-        """
-        GIVEN:
-            - A mock queryset
-        WHEN:
-            - len() is called on a _StreamedDocuments wrapping it
-        THEN:
-            - The queryset's count() is used, not a materializing len()
-        """
-        mock_queryset = mocker.MagicMock()
-        mock_queryset.count.return_value = 42
-
-        assert len(indexing._StreamedDocuments(mock_queryset)) == 42
-        mock_queryset.count.assert_called_once_with()
-
-    def test_iter_streams_via_queryset_iterator(
-        self,
-        mocker: pytest_mock.MockerFixture,
-    ) -> None:
-        """
-        GIVEN:
-            - A mock queryset whose .iterator() yields documents
-        WHEN:
-            - A _StreamedDocuments wrapping it is iterated
-        THEN:
-            - .iterator() is called with the streaming chunk size (not
-              plain iteration, which would materialize prefetches for the
-              whole queryset instead of one batch at a time), and its
-              results are yielded through unchanged
-        """
-        mock_queryset = mocker.MagicMock()
-        mock_queryset.iterator.return_value = iter(["doc-1", "doc-2"])
-
-        result = list(indexing._StreamedDocuments(mock_queryset))
-
-        assert result == ["doc-1", "doc-2"]
-        mock_queryset.iterator.assert_called_once_with(
-            chunk_size=indexing._INDEX_STREAM_CHUNK_SIZE,
-        )
-
-
 @pytest.mark.django_db
 def test_update_llm_index(
     temp_llm_index_dir: Path,