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

docs/configuration.md

@@ -948,11 +948,10 @@ for display in the web interface.
 
     !!! note
 
-        The **remote OCR parser** (Azure AI) also honors this setting: when
-        no archive is requested (`never`, or `auto` with a born-digital PDF),
-        the remote engine is skipped entirely and locally-extracted text is
-        used instead, avoiding an unnecessary API call and a duplicate text
-        layer.
+        The **remote OCR parser** (Azure AI) always produces a searchable
+        PDF and stores it as the archive copy, regardless of this setting.
+        `ARCHIVE_FILE_GENERATION=never` has no effect when the remote
+        parser handles a document.
 
 #### [`PAPERLESS_OCR_CLEAN=<mode>`](#PAPERLESS_OCR_CLEAN) {#PAPERLESS_OCR_CLEAN}
 

docs/migration-v3.md

@@ -187,11 +187,10 @@ PAPERLESS_ARCHIVE_FILE_GENERATION=auto
 
 ### Remote OCR parser
 
-If you use the **remote OCR parser** (Azure AI), `ARCHIVE_FILE_GENERATION` is
-honored the same way as for the local engine: when no archive is requested
-(`never`, or `auto` with a born-digital PDF), the remote engine is skipped
-entirely and locally-extracted text is used instead, avoiding an unnecessary
-API call and a duplicate text layer.
+If you use the **remote OCR parser** (Azure AI), note that it always produces a
+searchable PDF and stores it as the archive copy. `ARCHIVE_FILE_GENERATION=never`
+has no effect for documents handled by the remote parser - the archive is produced
+unconditionally by the remote engine.
 
 ## Search Index (Whoosh -> Tantivy)
 

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/parsers/remote.py

@@ -3,9 +3,7 @@ Built-in remote-OCR document parser.
 
 Handles documents by sending them to a configured remote OCR engine
 (currently Azure AI Vision / Document Intelligence) and retrieving both
-the extracted text and a searchable PDF with an embedded text layer. For
-born-digital PDFs that need no archive copy, the remote call is skipped
-entirely in favor of locally-extracted text (see ``RemoteDocumentParser.parse``).
+the extracted text and a searchable PDF with an embedded text layer.
 
 When no engine is configured, ``score()`` returns ``None`` so the parser
 is effectively invisible to the registry — the tesseract parser handles
@@ -23,8 +21,6 @@ from typing import Self
 
 from django.conf import settings
 
-from paperless.parsers.utils import extract_pdf_text
-from paperless.parsers.utils import post_process_text
 from paperless.version import __full_version_str__
 
 if TYPE_CHECKING:
@@ -73,11 +69,8 @@ class RemoteDocumentParser:
     """Parse documents via a remote OCR API (currently Azure AI Vision).
 
     This parser sends documents to a remote engine that returns both
-    extracted text and a searchable PDF with an embedded text layer,
-    except when ``parse()`` is called with ``produce_archive=False`` for
-    a PDF, in which case the remote call is skipped and only locally
-    extracted text is returned (no archive). It does not depend on
-    Tesseract or ocrmypdf.
+    extracted text and a searchable PDF with an embedded text layer.
+    It does not depend on Tesseract or ocrmypdf.
 
     Class attributes
     ----------------
@@ -166,11 +159,8 @@ class RemoteDocumentParser:
         Returns
         -------
         bool
-            Always True — the remote engine is capable of returning a PDF
-            with an embedded text layer to serve as the archive copy.
-            Whether it actually does so for a given document depends on
-            ``produce_archive`` passed to :meth:`parse` (see there for when
-            the remote engine call, and thus archive generation, is skipped).
+            Always True — the remote engine always returns a PDF with an
+            embedded text layer that serves as the archive copy.
         """
         return True
 
@@ -227,12 +217,6 @@ class RemoteDocumentParser:
     ) -> None:
         """Send the document to the remote engine and store results.
 
-        When *produce_archive* is False for a PDF, the caller (via
-        ``documents.consumer.should_produce_archive``) has already determined
-        that the document is born-digital and needs no archive — skip the
-        remote engine entirely rather than re-OCRing it and creating a
-        duplicate text layer.
-
         Parameters
         ----------
         document_path:
@@ -240,8 +224,8 @@ class RemoteDocumentParser:
         mime_type:
             Detected MIME type of the document.
         produce_archive:
-            Whether an archive copy is wanted. For PDFs, False skips the
-            remote engine and uses locally-extracted text instead.
+            Ignored — the remote engine always returns a searchable PDF,
+            which is stored as the archive copy regardless of this flag.
         """
         config = RemoteEngineConfig(
             engine=settings.REMOTE_OCR_ENGINE,
@@ -256,16 +240,6 @@ class RemoteDocumentParser:
             self._text = ""
             return
 
-        if not produce_archive and mime_type == "application/pdf":
-            logger.debug(
-                "Remote OCR: skipped — no archive requested, "
-                "using locally-extracted text",
-            )
-            self._text = (
-                post_process_text(extract_pdf_text(document_path, log=logger)) or ""
-            )
-            return
-
         if config.engine == "azureai":
             self._text = self._azure_ai_vision_parse(document_path, config)
 

src/paperless/parsers/tesseract.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import importlib.resources
 import logging
 import os
+import re
 import shutil
 import tempfile
 from pathlib import Path
@@ -24,9 +25,9 @@ from paperless.config import OcrConfig
 from paperless.models import CleanChoices
 from paperless.models import ModeChoices
 from paperless.models import OutputTypeChoices
+from paperless.parsers.utils import PDF_TEXT_MIN_LENGTH
 from paperless.parsers.utils import extract_pdf_text
-from paperless.parsers.utils import pdf_has_digital_text
-from paperless.parsers.utils import post_process_text
+from paperless.parsers.utils import is_tagged_pdf
 from paperless.parsers.utils import read_file_handle_unicode_errors
 from paperless.version import __full_version_str__
 
@@ -509,10 +510,10 @@ class RasterisedDocumentParser:
 
         if mime_type == "application/pdf":
             text_original = self.extract_text(None, document_path)
-            original_has_text = pdf_has_digital_text(
-                document_path,
-                text_original,
-                log=self.log,
+            has_text = text_original is not None and len(text_original) > 0
+            original_has_text = has_text and (
+                is_tagged_pdf(document_path, log=self.log)
+                or len(text_original) > PDF_TEXT_MIN_LENGTH
             )
         else:
             text_original = None
@@ -657,3 +658,17 @@ class RasterisedDocumentParser:
                     f"No text was found in {document_path}, the content will be empty.",
                 )
                 self.text = ""
+
+
+def post_process_text(text: str | None) -> str | None:
+    if not text:
+        return None
+
+    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
+    no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
+    no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
+
+    # TODO: this needs a rework
+    # replace \0 prevents issues with saving to postgres.
+    # text may contain \0 when this character is present in PDF files.
+    return no_trailing_whitespace.strip().replace("\0", " ")

src/paperless/parsers/utils.py

@@ -65,63 +65,6 @@ def is_tagged_pdf(
         return False
 
 
-def pdf_has_digital_text(
-    path: Path,
-    text: str | None,
-    log: logging.Logger | None = None,
-) -> bool:
-    """Return True if a PDF already has a usable, born-digital text layer.
-
-    Combines the tagged-PDF check with an extracted-text length check.
-    Shared by the tesseract and remote OCR parsers to decide whether
-    OCR_MODE=auto/off should skip (re-)OCRing a document.
-
-    Parameters
-    ----------
-    path:
-        Absolute path to the PDF file.
-    text:
-        Text already extracted from the PDF (e.g. via ``extract_pdf_text``),
-        or ``None``.
-    log:
-        Logger for warnings.  Falls back to the module-level logger when omitted.
-
-    Returns
-    -------
-    bool
-        ``True`` when the document already contains a text layer.
-    """
-    return is_tagged_pdf(path, log=log) or (
-        text is not None and len(text) > PDF_TEXT_MIN_LENGTH
-    )
-
-
-def post_process_text(text: str | None) -> str | None:
-    """Normalise whitespace in extracted OCR/PDF text and strip NUL bytes.
-
-    Parameters
-    ----------
-    text:
-        Raw extracted text, or ``None``.
-
-    Returns
-    -------
-    str | None
-        Cleaned text, or ``None`` when *text* is falsy.
-    """
-    if not text:
-        return None
-
-    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
-    no_leading_whitespace = re.sub(r"([\n\r]+)([^\S\n\r]+)", "\\1", collapsed_spaces)
-    no_trailing_whitespace = re.sub(r"([^\S\n\r]+)$", "", no_leading_whitespace)
-
-    # TODO: this needs a rework
-    # replace \0 prevents issues with saving to postgres.
-    # text may contain \0 when this character is present in PDF files.
-    return no_trailing_whitespace.strip().replace("\0", " ")
-
-
 def extract_pdf_text(
     path: Path,
     log: logging.Logger | None = None,

src/paperless/tests/parsers/test_remote_parser.py

@@ -336,117 +336,6 @@ class TestRemoteParserParse:
         assert remote_parser.get_date() is None
 
 
-# ---------------------------------------------------------------------------
-# parse() — produce_archive=False skips the remote engine (PDFs only)
-# ---------------------------------------------------------------------------
-
-
-class TestRemoteParserSkipsWhenNoArchiveWanted:
-    """When the caller has already decided no archive is needed for a PDF
-    (documents.consumer.should_produce_archive), the remote engine call is
-    skipped entirely in favor of locally-extracted text.
-    """
-
-    def test_pdf_skips_azure_when_no_archive_requested(
-        self,
-        remote_parser: RemoteDocumentParser,
-        simple_digital_pdf_file: Path,
-        azure_client: Mock,
-    ) -> None:
-        """
-        GIVEN: produce_archive=False for a PDF
-        WHEN:  parse() is called
-        THEN:  Azure is never invoked, no archive is produced, and text
-               comes from local pdftotext extraction
-        """
-        remote_parser.parse(
-            simple_digital_pdf_file,
-            "application/pdf",
-            produce_archive=False,
-        )
-
-        azure_client.begin_analyze_document.assert_not_called()
-        assert remote_parser.get_archive_path() is None
-        assert remote_parser.get_text() != ""
-
-    def test_pdf_no_archive_requested_text_matches_local_extraction(
-        self,
-        remote_parser: RemoteDocumentParser,
-        simple_digital_pdf_file: Path,
-        azure_client: Mock,
-        mocker: MockerFixture,
-    ) -> None:
-        """
-        GIVEN: produce_archive=False for a PDF
-        WHEN:  parse() is called
-        THEN:  the returned text is exactly the locally-extracted text,
-               not anything from the (unused) Azure mock
-        """
-        mocker.patch(
-            "paperless.parsers.remote.extract_pdf_text",
-            return_value="Local digital text.",
-        )
-
-        remote_parser.parse(
-            simple_digital_pdf_file,
-            "application/pdf",
-            produce_archive=False,
-        )
-
-        assert remote_parser.get_text() == "Local digital text."
-
-    def test_pdf_no_archive_requested_closes_no_client(
-        self,
-        remote_parser: RemoteDocumentParser,
-        simple_digital_pdf_file: Path,
-        azure_client: Mock,
-    ) -> None:
-        remote_parser.parse(
-            simple_digital_pdf_file,
-            "application/pdf",
-            produce_archive=False,
-        )
-
-        azure_client.close.assert_not_called()
-
-    def test_non_pdf_still_calls_azure_when_no_archive_requested(
-        self,
-        remote_parser: RemoteDocumentParser,
-        simple_digital_pdf_file: Path,
-        azure_client: Mock,
-    ) -> None:
-        """
-        Images have no local-text fallback, so produce_archive=False does
-        not skip the remote engine for non-PDF MIME types.
-        """
-        remote_parser.parse(
-            simple_digital_pdf_file,
-            "image/png",
-            produce_archive=False,
-        )
-
-        azure_client.begin_analyze_document.assert_called_once()
-        assert remote_parser.get_text() == _DEFAULT_TEXT
-
-    @pytest.mark.usefixtures("no_engine_settings")
-    def test_unconfigured_engine_takes_precedence_over_skip(
-        self,
-        remote_parser: RemoteDocumentParser,
-        simple_digital_pdf_file: Path,
-    ) -> None:
-        """An unconfigured engine still short-circuits before the
-        produce_archive check, returning empty text as before.
-        """
-        remote_parser.parse(
-            simple_digital_pdf_file,
-            "application/pdf",
-            produce_archive=False,
-        )
-
-        assert remote_parser.get_text() == ""
-        assert remote_parser.get_archive_path() is None
-
-
 # ---------------------------------------------------------------------------
 # parse() — Azure failure path
 # ---------------------------------------------------------------------------

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -21,7 +21,7 @@ from documents.parsers import run_convert
 from paperless.models import ModeChoices
 from paperless.parsers import ParserProtocol
 from paperless.parsers.tesseract import RasterisedDocumentParser
-from paperless.parsers.utils import post_process_text
+from paperless.parsers.tesseract import post_process_text
 
 if TYPE_CHECKING:
     from pathlib import Path