Fix #156 - NoneType has no ‘getObject’ for pages with no /Contents

ocrmypdf/pageinfo.py

@@ -430,7 +430,7 @@ def _find_images(pdf, container, shorthand=None):
 
     """
 
-    if container.get('/Type') == '/Page':
+    if container.get('/Type') == '/Page' and '/Contents' in container:
         # For a /Page the content stream is attached to the page's /Contents
         page = container
         contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)

tests/resources/README.rst

@@ -85,6 +85,9 @@ under the terms of the license in LICENSE.rst.
     *   - overlay.pdf
         - @maxandersen
         - PDF file generated by PDFPen pro that triggered content stream parse errors
+    *   - no_conentes.pdf
+        - @jbarlow83
+        - synthetic PDF with a blank page that has no /Contents entry
 
 Assemblies
 ==========

tests/resources/no_contents.pdf

@@ -0,0 +1,21 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /MediaBox [ 0 0 720 720 ] /Parent 2 0 R /Resources << >> /Type /Page >>
+endobj
+xref
+0 4
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+trailer << /Root 1 0 R /Size 4 /ID [<52bba3c78160d0c6e851b59110e5d076><52bba3c78160d0c6e851b59110e5d076>] >>
+startxref
+213
+%%EOF

tests/test_main.py

@@ -870,4 +870,8 @@ def test_gs_raster_failure(spoof_no_tess_gs_raster_fail, resources, outpdf):
         env=spoof_no_tess_gs_raster_fail)
     print(err)
     assert p.returncode == ExitCode.child_process_error
+
+
+def test_no_contents(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'no_contents.pdf', outpdf, '--force-ocr',
                    env=spoof_tesseract_noop)

tests/test_pageinfo.py

@@ -108,3 +108,11 @@ def test_form_xobject(resources):
     pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['width'] == 50
+
+
+def test_no_contents(resources):
+    filename = resources / 'no_contents.pdf'
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+    assert len(pdfinfo[0]['images']) == 0
+    assert pdfinfo[0]['has_text'] == False