v6.1.4 fix test suite regression with Ghostscript 9.23

docs/release_notes.rst

@@ -16,6 +16,8 @@ v6.1.4
 
 -   The test cache was updated to reflect the change above.
 
+-   Change test suite to accommodate Ghostscript 9.23's new ability to insert JPEGs into PDFs without transcoding.  An apparent `regression in Ghostscript 9.23 <https://bugs.ghostscript.com/show_bug.cgi?id=699216>`_ will cause some ocrmypdf output files to become invalid in rare cases; the workaround for the moment is to set ``--force-ocr``.
+
 -   XMP metadata in PDFs is now examined using ``defusedxml`` for safety.
 
 -   If an external process exits with a signal when asked to report its version, we now print the system error message instead of suppressing it.  This occurred when the required executable was found but was missing a shared library.

src/ocrmypdf/exec/ghostscript.py

@@ -137,7 +137,7 @@ def generate_pdfa(pdf_pages, output_file, compression, log,
             "-dNumRenderingThreads=" + str(threads),
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=/RGB",
+            "-sColorConversionStrategy=RGB",
             "-sProcessColorModel=DeviceRGB"
         ] + compression_args + [
             "-dJPEGQ=95",

tests/test_main.py

@@ -607,7 +607,14 @@ def test_closed_streams(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
 
 
 def test_masks(spoof_tesseract_noop, resources, outpdf):
-    check_ocrmypdf(resources / 'masks.pdf', outpdf, env=spoof_tesseract_noop)
+    p, out, err = run_ocrmypdf(
+        resources / 'masks.pdf', outpdf, env=spoof_tesseract_noop)
+
+    if ghostscript.version() == '9.23' and \
+            p.returncode == ExitCode.invalid_output_pdf:
+        pytest.xfail('https://bugs.ghostscript.com/show_bug.cgi?id=699216')
+
+    assert p.returncode == ExitCode.ok
 
 
 def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop,
@@ -898,8 +905,14 @@ def test_compression_changed(spoof_tesseract_noop, ocrmypdf_exec,
 
     if compression == "jpeg":
         assert pdfimage.enc == Encoding.jpeg
-    elif compression == 'lossless':
-        assert pdfimage.enc not in (Encoding.jpeg, Encoding.jpeg2000)
+    else:
+        if ghostscript.version() >= '9.23':
+            # Ghostscript 9.23 adds JPEG passthrough, which allows a JPEG to be
+            # copied without transcoding - so report
+            if image.endswith('jpg'):
+                assert pdfimage.enc == Encoding.jpeg
+        else:
+            assert pdfimage.enc not in (Encoding.jpeg, Encoding.jpeg2000)
 
     if im.mode.startswith('RGB') or im.mode.startswith('BGR'):
         assert pdfimage.color == Colorspace.rgb, \