Merge branch 'dev'

src/paperless/migrations/0007_optimize_integer_field_sizes.py

@@ -5,12 +5,30 @@ from django.db import migrations
 from django.db import models
 
 
+def clamp_applicationconfiguration_integer_fields(apps, schema_editor):
+    # Clamp barcode_dpi, barcode_max_pages, image_dpi and pages because of
+    # PositiveIntegerField --> PositiveSmallIntegerField
+    ApplicationConfiguration = apps.get_model("paperless", "ApplicationConfiguration")
+    ApplicationConfiguration.objects.filter(barcode_dpi__gt=32767).update(
+        barcode_dpi=32767,
+    )
+    ApplicationConfiguration.objects.filter(barcode_max_pages__gt=32767).update(
+        barcode_max_pages=32767,
+    )
+    ApplicationConfiguration.objects.filter(image_dpi__gt=32767).update(image_dpi=32767)
+    ApplicationConfiguration.objects.filter(pages__gt=32767).update(pages=32767)
+
+
 class Migration(migrations.Migration):
     dependencies = [
         ("paperless", "0006_applicationconfiguration_barcode_tag_split"),
     ]
 
     operations = [
+        migrations.RunPython(
+            clamp_applicationconfiguration_integer_fields,
+            migrations.RunPython.noop,
+        ),
         migrations.AlterField(
             model_name="applicationconfiguration",
             name="barcode_dpi",

src/paperless/parsers/tesseract.py

@@ -510,8 +510,10 @@ class RasterisedDocumentParser:
 
         if mime_type == "application/pdf":
             text_original = self.extract_text(None, document_path)
-            original_has_text = is_tagged_pdf(document_path, log=self.log) or (
-                text_original is not None and len(text_original) > PDF_TEXT_MIN_LENGTH
+            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

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -906,6 +906,34 @@ class TestSkipArchive:
         assert tesseract_parser.archive_path is None
         assert tesseract_parser.get_text()
 
+    def test_tagged_pdf_without_text_does_not_skip_ocr(
+        self,
+        mocker: MockerFixture,
+        tesseract_parser: RasterisedDocumentParser,
+        tesseract_samples_dir: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A PDF that reports itself as tagged (/MarkInfo /Marked true) but
+              has no actual extractable text (some scanner firmware produces
+              this — see GitHub issue #13349)
+            - Mode: auto, produce_archive=False
+        WHEN:
+            - Document is parsed
+        THEN:
+            - The tag alone is not trusted as "has text"; OCRmyPDF still runs
+        """
+        tesseract_parser.settings.mode = ModeChoices.AUTO
+        mocker.patch("paperless.parsers.tesseract.is_tagged_pdf", return_value=True)
+        mocker.patch.object(tesseract_parser, "extract_text", return_value=None)
+        mock_ocr = mocker.patch("ocrmypdf.ocr")
+        tesseract_parser.parse(
+            tesseract_samples_dir / "multi-page-images.pdf",
+            "application/pdf",
+            produce_archive=False,
+        )
+        mock_ocr.assert_called()
+
     def test_tagged_pdf_produces_pdfa_archive_without_ocr(
         self,
         tesseract_parser: RasterisedDocumentParser,