Merge img2pdf 0.3.0 fix from v6.2.3

docs/release_notes.rst

@@ -13,6 +13,11 @@ Note that it is licensed under GPLv3, so scripts that ``import ocrmypdf`` and ar
    find:    [^`]\#([0-9]{1,3})[^0-9]
    replace: `#$1 <https://github.com/jbarlow83/OCRmyPDF/issues/$1>`_
 
+v7.0.1
+------
+
+-   Fix compatibility with img2pdf >= 0.3.0 by rejecting input images that have an alpha channel
+
 v7.0.0
 ------
 
@@ -61,6 +66,12 @@ v7.0.0
 
     +   It may be necessary to separately ``pip install pycparser`` to avoid `another Python 3.7 issue <https://github.com/eliben/pycparser/pull/135>`_.
 
+v6.2.3
+------
+
+-   Fix compatibility with img2pdf >= 0.3.0 by rejecting input images that have an alpha channel
+
+
 v6.2.2
 ------
 

src/ocrmypdf/_pipeline.py

@@ -19,7 +19,6 @@ from contextlib import suppress
 from shutil import copyfileobj, copyfile
 from pathlib import Path
 from datetime import datetime, timezone
-
 import sys
 import os
 import re
@@ -85,6 +84,13 @@ def triage_image_file(input_file, output_file, log, options):
                 "image was scanned and specify it using --image-dpi.")
             raise DpiError()
 
+        if im.mode in ('RGBA', 'LA'):
+            log.error(
+                "The input image has an alpha channel. Remove the alpha "
+                "channel first."
+            )
+            raise UnsupportedImageFormatError()
+
         if 'iccprofile' not in im.info:
             if im.mode == 'RGB':
                 log.info('Input image has no ICC profile, assuming sRGB')

tests/resources/README.rst

@@ -146,8 +146,9 @@ Assemblies
 
 These test resources are assemblies or derivatives from other previously mentioned files, released under the same license terms as their input files.
 
-- baiona_gray.png (from baiona.png)
-- baiona_colormapped.png (from baiona.png)
+- baiona_gray.png (from baiona.png, grayscale version)
+- baiona_colormapped.png (from baiona.png, palette version)
+- baiona_alpha.png (from baiona.png, RGB+A version)
 - cardinal.pdf (four cardinal directions, baked-in rotated copies of linn.png)
 - ccitt.pdf (linn.png, converted to CCITT encoding)
 - encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)

tests/test_main.py

@@ -691,6 +691,7 @@ def test_no_contents(spoof_tesseract_noop, resources, outpdf):
 @pytest.mark.parametrize('image', [
     'baiona.png',
     'baiona_gray.png',
+    'baiona_alpha.png',
     'congress.jpg'
     ])
 def test_compression_preserved(spoof_tesseract_noop, ocrmypdf_exec,
@@ -699,7 +700,6 @@ def test_compression_preserved(spoof_tesseract_noop, ocrmypdf_exec,
     output_file = str(outpdf)
 
     im = Image.open(input_file)
-
     # Runs: ocrmypdf - output.pdf < testfile
     with open(input_file, 'rb') as input_stream:
         p_args = ocrmypdf_exec + [
@@ -710,7 +710,12 @@ def test_compression_preserved(spoof_tesseract_noop, ocrmypdf_exec,
             stdin=input_stream, env=spoof_tesseract_noop)
         out, err = p.communicate()
 
-        assert p.returncode == ExitCode.ok
+        if im.mode in ('RGBA', 'LA'):
+            # If alpha image is input, expect an error
+            assert p.returncode != ExitCode.ok and b'alpha' in err
+            return
+
+        assert p.returncode == ExitCode.ok, err.decode('utf-8')
 
     pdfinfo = PdfInfo(output_file)
 
@@ -754,7 +759,7 @@ def test_compression_changed(spoof_tesseract_noop, ocrmypdf_exec,
             stdin=input_stream, env=spoof_tesseract_noop)
         out, err = p.communicate()
 
-        assert p.returncode == ExitCode.ok
+        assert p.returncode == ExitCode.ok, err
 
     pdfinfo = PdfInfo(output_file)