Add Encoding.flate_jpeg to recognize deflated JPEG images

FlateDecode+DCTDecode compressed images are essentially deflated JPEGs,
typically created by OCRmyPDF's optimizer. This change ensures pdfinfo
correctly identifies them and should_visible_page_image_use_jpg treats
them as JPEG-origin images, allowing JPEG output when appropriate.

src/ocrmypdf/_pipeline.py

@@ -735,7 +735,8 @@ def ocr_engine_direct(
 def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
     """Determines whether the visible page image should be saved as a JPEG.
 
-    If all images were JPEGs originally, permit a JPEG as output.
+    If all images were JPEGs originally (including FlateDecode+DCTDecode),
+    permit a JPEG as output.
 
     Args:
         pageinfo: The PageInfo object containing information about the page.
@@ -744,7 +745,7 @@ def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
         A boolean indicating whether the visible page image should be saved as a JPEG.
     """
     return bool(pageinfo.images) and all(
-        im.enc == Encoding.jpeg for im in pageinfo.images
+        im.enc in (Encoding.jpeg, Encoding.flate_jpeg) for im in pageinfo.images
     )
 
 

src/ocrmypdf/pdfinfo/_image.py

@@ -108,10 +108,18 @@ class ImageInfo:
             self._type = 'image'
 
         self._bpc = int(pim.bits_per_component)
-        try:
-            self._enc = FRIENDLY_ENCODING.get(pim.filters[0])
-        except IndexError:
-            self._enc = None
+        if (
+            len(pim.filters) == 2
+            and pim.filters[0] == '/FlateDecode'
+            and pim.filters[1] == '/DCTDecode'
+        ):
+            # Special case: FlateDecode followed by DCTDecode
+            self._enc = Encoding.flate_jpeg
+        else:
+            try:
+                self._enc = FRIENDLY_ENCODING.get(pim.filters[0])
+            except IndexError:
+                self._enc = None
 
         try:
             self._color = FRIENDLY_COLORSPACE.get(pim.colorspace or '')

src/ocrmypdf/pdfinfo/_types.py

@@ -36,6 +36,7 @@ class Encoding(Enum):
     lzw = auto()
     flate = auto()
     runlength = auto()
+    flate_jpeg = auto()
 
 
 FloatRect = tuple[float, float, float, float]

tests/test_pdfinfo.py

@@ -131,6 +131,55 @@ def test_jpeg(resources):
     assert isclose(pdfimage.dpi.x, 150)
 
 
+@pytest.fixture
+def flate_jpeg_pdf(outpdf):
+    """Create a PDF with a FlateDecode+DCTDecode (flate+jpeg) encoded image.
+
+    This simulates what OCRmyPDF's optimizer does when it deflates JPEGs.
+    """
+    from zlib import compress
+
+    # Create an RGB image and save as JPEG
+    im = Image.new('RGB', (64, 64), color=(128, 64, 192))
+    bio = BytesIO()
+    im.save(bio, format='JPEG')
+    jpeg_data = bio.getvalue()
+
+    # Compress the JPEG data with flate
+    flate_jpeg_data = compress(jpeg_data)
+
+    # Create a PDF with the flate+jpeg image
+    with pikepdf.Pdf.new() as pdf:
+        pdf.add_blank_page(page_size=(72, 72))
+        image_dict = pikepdf.Stream(
+            pdf,
+            flate_jpeg_data,
+            BitsPerComponent=8,
+            ColorSpace=pikepdf.Name.DeviceRGB,
+            Filter=[pikepdf.Name.FlateDecode, pikepdf.Name.DCTDecode],
+            Height=64,
+            Subtype=pikepdf.Name.Image,
+            Type=pikepdf.Name.XObject,
+            Width=64,
+        )
+        objname = pdf.pages[0].add_resource(
+            image_dict, pikepdf.Name.XObject, pikepdf.Name.Im0
+        )
+        pdf.pages[0].Contents = pikepdf.Stream(
+            pdf, b"q 72 0 0 72 0 0 cm %s Do Q" % bytes(objname)
+        )
+        pdf.save(outpdf)
+    return outpdf
+
+
+def test_flate_jpeg(flate_jpeg_pdf):
+    """Test that pdfinfo correctly identifies FlateDecode+DCTDecode as flate_jpeg."""
+    pdf = pdfinfo.PdfInfo(flate_jpeg_pdf)
+
+    pdfimage = pdf[0].images[0]
+    assert pdfimage.enc == Encoding.flate_jpeg
+
+
 def test_form_xobject(resources):
     filename = resources / 'formxobject.pdf'
 

tests/test_pipeline.py

@@ -14,6 +14,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import _pipeline, pdfinfo
 from ocrmypdf.helpers import Resolution
+from ocrmypdf.pdfinfo import Encoding
 
 warnings.filterwarnings(
     "ignore", category=DeprecationWarning, module="reportlab.lib.rl_safe_eval"
@@ -150,3 +151,28 @@ def test_dpi_needed(image, text, vector, result, rgb_image, outdir):
 )
 def test_enumerate_compress_ranges(name, input, output):
     assert output == tuple(_pipeline.enumerate_compress_ranges(input))
+
+
+@pytest.mark.parametrize(
+    'encodings, expected',
+    [
+        # Empty images list returns False
+        ([], False),
+        # Single JPEG returns True
+        ([Encoding.jpeg], True),
+        # Single flate_jpeg returns True
+        ([Encoding.flate_jpeg], True),
+        # Mix of jpeg and flate_jpeg returns True
+        ([Encoding.jpeg, Encoding.flate_jpeg], True),
+        # Non-JPEG encoding returns False
+        ([Encoding.flate], False),
+        # Mix with non-JPEG returns False
+        ([Encoding.jpeg, Encoding.flate], False),
+        ([Encoding.flate_jpeg, Encoding.flate], False),
+    ],
+)
+def test_should_visible_page_image_use_jpg(encodings, expected):
+    """Test that should_visible_page_image_use_jpg correctly handles flate_jpeg."""
+    pageinfo = Mock()
+    pageinfo.images = [Mock(enc=enc) for enc in encodings]
+    assert _pipeline.should_visible_page_image_use_jpg(pageinfo) == expected