Fix: ignore invalid EXIF orientation when generating image archives (#14203)

Images with an out-of-spec EXIF orientation value (e.g. 0) fail
conversion with img2pdf.ExifOrientationError, which aborts archive
generation and, during consumption with OCR disabled, fails the whole
document.

Pass rotation=img2pdf.Rotation.ifvalid so invalid orientation values
are ignored while valid values (1, 3, 6, 8) are still applied.

Co-authored-by: zhzy0077 <zhzy0077@users.noreply.github.com>

src/paperless/parsers/tesseract.py

@@ -394,7 +394,11 @@ class RasterisedDocumentParser:
 
         plain_pdf_path = Path(self.tempdir) / "image_plain.pdf"
         try:
-            convert_kwargs: dict = {}
+            convert_kwargs: dict = {
+                # Ignore invalid EXIF orientation values (e.g. 0) instead of
+                # aborting the conversion; valid values are still applied
+                "rotation": img2pdf.Rotation.ifvalid,
+            }
             if self.settings.image_dpi is not None:
                 convert_kwargs["layout_fun"] = img2pdf.get_fixed_dpi_layout_fun(
                     (self.settings.image_dpi, self.settings.image_dpi),

src/paperless/tests/parsers/test_convert_image_to_pdfa.py

@@ -18,6 +18,7 @@ import img2pdf
 import magic
 import pikepdf
 import pytest
+from PIL import Image
 
 from documents.parsers import ParseError
 
@@ -139,3 +140,24 @@ class TestConvertImageToPdfa:
         tesseract_parser._convert_image_to_pdfa(simple_png_file)
 
         spy.assert_not_called()
+
+    def test_invalid_exif_orientation_is_ignored(
+        self,
+        tesseract_parser: RasterisedDocumentParser,
+        tmp_path: Path,
+    ) -> None:
+        """
+        GIVEN: a JPEG with an invalid EXIF orientation value (0)
+        WHEN: _convert_image_to_pdfa is called
+        THEN: the invalid value is ignored and a valid PDF is produced
+        """
+        image_path = tmp_path / "invalid_orientation.jpg"
+        with Image.new("RGB", (120, 80), "white") as image:
+            exif = image.getexif()
+            exif[274] = 0  # EXIF tag 274: Orientation
+            image.save(image_path, exif=exif)
+
+        result = tesseract_parser._convert_image_to_pdfa(image_path)
+
+        assert result.exists()
+        assert magic.from_file(str(result), mime=True) == "application/pdf"