Discard alpha channel when triaging images

src/ocrmypdf/helpers.py

@@ -15,6 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
+from PIL import Image
+
 from functools import partial
 from collections.abc import Iterable
 from contextlib import suppress, contextmanager
@@ -128,6 +130,15 @@ def is_file_writable(test_file):
         return True
 
 
+def discard_alpha(im):
+    if im.mode in ('RGBA', 'LA'):
+        fill_color = (1, 1, 1) if im.mode == 'RGBA' else 1
+        backgd = Image.new(im.mode[:-1], im.size, fill_color)
+        backgd.paste(im, im.split()[-1])
+        im = backgd
+    return im
+
+
 if sys.version_info[0:2] <= (3, 5):
     def universal_open(p, *args, **kwargs):
         "Work around Python 3.5's inability to open(pathlib.Path())"

src/ocrmypdf/pipeline.py

@@ -19,6 +19,7 @@ from contextlib import suppress
 from shutil import copyfileobj
 from pathlib import Path
 from datetime import datetime, timezone
+from io import BytesIO
 import sys
 import os
 import shutil
@@ -33,7 +34,7 @@ from ruffus import formatter, regex, Pipeline, suffix
 from .hocrtransform import HocrTransform
 from .pdfinfo import PdfInfo, Encoding, Colorspace
 from .pdfa import generate_pdfa_ps, encode_pdf_date
-from .helpers import re_symlink, is_iterable_notstr, page_number
+from .helpers import re_symlink, is_iterable_notstr, page_number, discard_alpha
 from .exec import ghostscript, tesseract, qpdf
 from .lib import fitz
 from .exceptions import PdfMergeFailedError, UnsupportedImageFormatError, \
@@ -159,8 +160,14 @@ def triage_image_file(input_file, output_file, log, options):
             layout_fun = img2pdf.get_fixed_dpi_layout_fun(
                 (options.image_dpi, options.image_dpi))
         with open(output_file, 'wb') as outf:
+            im = Image.open(input_file)
+            im_format = im.format
+            im = discard_alpha(im)
+            im_bio = BytesIO()
+            im.save(im_bio, format=im_format)
+            im_bio.seek(0)
             img2pdf.convert(
-                input_file,
+                im_bio,
                 layout_fun=layout_fun,
                 with_pdfrw=False,
                 outputstream=outf)

tests/test_main.py

@@ -849,7 +849,7 @@ 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
+        assert p.returncode == ExitCode.ok, err.decode('utf-8')
 
     pdfinfo = PdfInfo(output_file)